1/*M///////////////////////////////////////////////////////////////////////////////////////
2//
3// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
4//
5// By downloading, copying, installing or using the software you agree to this license.
6// If you do not agree to this license, do not download, install,
7// copy or use the software.
8//
9//
10// License Agreement
11// For Open Source Computer Vision Library
12//
13// Copyright (C) 2000-2008, Intel Corporation, all rights reserved.
14// Copyright (C) 2009, Willow Garage Inc., all rights reserved.
15// Third party copyrights are property of their respective owners.
16//
17// Redistribution and use in source and binary forms, with or without modification,
18// are permitted provided that the following conditions are met:
19//
20// * Redistribution's of source code must retain the above copyright notice,
21// this list of conditions and the following disclaimer.
22//
23// * Redistribution's in binary form must reproduce the above copyright notice,
24// this list of conditions and the following disclaimer in the documentation
25// and/or other materials provided with the distribution.
26//
27// * The name of the copyright holders may not be used to endorse or promote products
28// derived from this software without specific prior written permission.
29//
30// This software is provided by the copyright holders and contributors "as is" and
31// any express or implied warranties, including, but not limited to, the implied
32// warranties of merchantability and fitness for a particular purpose are disclaimed.
33// In no event shall the Intel Corporation or contributors be liable for any direct,
34// indirect, incidental, special, exemplary, or consequential damages
35// (including, but not limited to, procurement of substitute goods or services;
36// loss of use, data, or profits; or business interruption) however caused
37// and on any theory of liability, whether in contract, strict liability,
38// or tort (including negligence or otherwise) arising in any way out of
39// the use of this software, even if advised of the possibility of such damage.
40//
41//M*/
42
43#ifndef OPENCV_IMGCODECS_HPP
44#define OPENCV_IMGCODECS_HPP
45
46#include "opencv2/core.hpp"
47
48/**
49 @defgroup imgcodecs Image file reading and writing
50 @{
51 @defgroup imgcodecs_flags Flags used for image file reading and writing
52 @defgroup imgcodecs_ios iOS glue
53 @defgroup imgcodecs_macosx MacOS(OSX) glue
54 @}
55*/
56
57//////////////////////////////// image codec ////////////////////////////////
58namespace cv
59{
60
61//! @addtogroup imgcodecs
62//! @{
63
64//! @addtogroup imgcodecs_flags
65//! @{
66
67//! Imread flags
68//! @note IMREAD_COLOR_BGR (IMREAD_COLOR) and IMREAD_COLOR_RGB can not be set at the same time.
69enum ImreadModes {
70 IMREAD_UNCHANGED = -1, //!< If set, return the loaded image as is (with alpha channel, otherwise it gets cropped). Ignore EXIF orientation.
71 IMREAD_GRAYSCALE = 0, //!< If set, always convert image to the single channel grayscale image (codec internal conversion).
72 IMREAD_COLOR_BGR = 1, //!< If set, always convert image to the 3 channel BGR color image.
73 IMREAD_COLOR = 1, //!< Same as IMREAD_COLOR_BGR.
74 IMREAD_ANYDEPTH = 2, //!< If set, return 16-bit/32-bit image when the input has the corresponding depth, otherwise convert it to 8-bit.
75 IMREAD_ANYCOLOR = 4, //!< If set, the image is read in any possible color format.
76 IMREAD_LOAD_GDAL = 8, //!< If set, use the gdal driver for loading the image.
77 IMREAD_REDUCED_GRAYSCALE_2 = 16, //!< If set, always convert image to the single channel grayscale image and the image size reduced 1/2.
78 IMREAD_REDUCED_COLOR_2 = 17, //!< If set, always convert image to the 3 channel BGR color image and the image size reduced 1/2.
79 IMREAD_REDUCED_GRAYSCALE_4 = 32, //!< If set, always convert image to the single channel grayscale image and the image size reduced 1/4.
80 IMREAD_REDUCED_COLOR_4 = 33, //!< If set, always convert image to the 3 channel BGR color image and the image size reduced 1/4.
81 IMREAD_REDUCED_GRAYSCALE_8 = 64, //!< If set, always convert image to the single channel grayscale image and the image size reduced 1/8.
82 IMREAD_REDUCED_COLOR_8 = 65, //!< If set, always convert image to the 3 channel BGR color image and the image size reduced 1/8.
83 IMREAD_IGNORE_ORIENTATION = 128, //!< If set, do not rotate the image according to EXIF's orientation flag.
84 IMREAD_COLOR_RGB = 256, //!< If set, always convert image to the 3 channel RGB color image.
85 };
86
87//! Imwrite flags
88enum ImwriteFlags {
89 IMWRITE_JPEG_QUALITY = 1, //!< For JPEG, it can be a quality from 0 to 100 (the higher is the better). Default value is 95.
90 IMWRITE_JPEG_PROGRESSIVE = 2, //!< Enable JPEG features, 0 or 1, default is False.
91 IMWRITE_JPEG_OPTIMIZE = 3, //!< Enable JPEG features, 0 or 1, default is False.
92 IMWRITE_JPEG_RST_INTERVAL = 4, //!< JPEG restart interval, 0 - 65535, default is 0 - no restart.
93 IMWRITE_JPEG_LUMA_QUALITY = 5, //!< Separate luma quality level, 0 - 100, default is -1 - don't use. If JPEG_LIB_VERSION < 70, Not supported.
94 IMWRITE_JPEG_CHROMA_QUALITY = 6, //!< Separate chroma quality level, 0 - 100, default is -1 - don't use. If JPEG_LIB_VERSION < 70, Not supported.
95 IMWRITE_JPEG_SAMPLING_FACTOR = 7, //!< For JPEG, set sampling factor. See cv::ImwriteJPEGSamplingFactorParams.
96 IMWRITE_PNG_COMPRESSION = 16, //!< For PNG, it can be the compression level from 0 to 9. A higher value means a smaller size and longer compression time. If specified, strategy is changed to IMWRITE_PNG_STRATEGY_DEFAULT (Z_DEFAULT_STRATEGY). Default value is 1 (best speed setting).
97 IMWRITE_PNG_STRATEGY = 17, //!< One of cv::ImwritePNGFlags, default is IMWRITE_PNG_STRATEGY_RLE.
98 IMWRITE_PNG_BILEVEL = 18, //!< Binary level PNG, 0 or 1, default is 0.
99 IMWRITE_PNG_FILTER = 19, //!< One of cv::ImwritePNGFilterFlags, default is IMWRITE_PNG_FILTER_SUB.
100 IMWRITE_PXM_BINARY = 32, //!< For PPM, PGM, or PBM, it can be a binary format flag, 0 or 1. Default value is 1.
101 IMWRITE_EXR_TYPE = (3 << 4) + 0 /* 48 */, //!< override EXR storage type (FLOAT (FP32) is default)
102 IMWRITE_EXR_COMPRESSION = (3 << 4) + 1 /* 49 */, //!< override EXR compression type (ZIP_COMPRESSION = 3 is default)
103 IMWRITE_EXR_DWA_COMPRESSION_LEVEL = (3 << 4) + 2 /* 50 */, //!< override EXR DWA compression level (45 is default)
104 IMWRITE_WEBP_QUALITY = 64, //!< For WEBP, it can be a quality from 1 to 100 (the higher is the better). By default (without any parameter) and for quality above 100 the lossless compression is used.
105 IMWRITE_HDR_COMPRESSION = (5 << 4) + 0 /* 80 */, //!< specify HDR compression
106 IMWRITE_PAM_TUPLETYPE = 128,//!< For PAM, sets the TUPLETYPE field to the corresponding string value that is defined for the format
107 IMWRITE_TIFF_RESUNIT = 256,//!< For TIFF, use to specify which DPI resolution unit to set; see libtiff documentation for valid values
108 IMWRITE_TIFF_XDPI = 257,//!< For TIFF, use to specify the X direction DPI
109 IMWRITE_TIFF_YDPI = 258,//!< For TIFF, use to specify the Y direction DPI
110 IMWRITE_TIFF_COMPRESSION = 259,//!< For TIFF, use to specify the image compression scheme. See cv::ImwriteTiffCompressionFlags. Note, for images whose depth is CV_32F, only libtiff's SGILOG compression scheme is used. For other supported depths, the compression scheme can be specified by this flag; LZW compression is the default.
111 IMWRITE_TIFF_ROWSPERSTRIP = 278,//!< For TIFF, use to specify the number of rows per strip.
112 IMWRITE_TIFF_PREDICTOR = 317,//!< For TIFF, use to specify predictor. See cv::ImwriteTiffPredictorFlags.
113 IMWRITE_JPEG2000_COMPRESSION_X1000 = 272,//!< For JPEG2000, use to specify the target compression rate (multiplied by 1000). The value can be from 0 to 1000. Default is 1000.
114 IMWRITE_AVIF_QUALITY = 512,//!< For AVIF, it can be a quality between 0 and 100 (the higher the better). Default is 95.
115 IMWRITE_AVIF_DEPTH = 513,//!< For AVIF, it can be 8, 10 or 12. If >8, it is stored/read as CV_32F. Default is 8.
116 IMWRITE_AVIF_SPEED = 514,//!< For AVIF, it is between 0 (slowest) and (fastest). Default is 9.
117 IMWRITE_JPEGXL_QUALITY = 640,//!< For JPEG XL, it can be a quality from 0 to 100 (the higher is the better). Default value is 95. If set, distance parameter is re-calicurated from quality level automatically. This parameter request libjxl v0.10 or later.
118 IMWRITE_JPEGXL_EFFORT = 641,//!< For JPEG XL, encoder effort/speed level without affecting decoding speed; it is between 1 (fastest) and 10 (slowest). Default is 7.
119 IMWRITE_JPEGXL_DISTANCE = 642,//!< For JPEG XL, distance level for lossy compression: target max butteraugli distance, lower = higher quality, 0 = lossless; range: 0 .. 25. Default is 1.
120 IMWRITE_JPEGXL_DECODING_SPEED = 643,//!< For JPEG XL, decoding speed tier for the provided options; minimum is 0 (slowest to decode, best quality/density), and maximum is 4 (fastest to decode, at the cost of some quality/density). Default is 0.
121 IMWRITE_GIF_LOOP = 1024, //!< Not functional since 4.12.0. Replaced by cv::Animation::loop_count.
122 IMWRITE_GIF_SPEED = 1025, //!< Not functional since 4.12.0. Replaced by cv::Animation::durations.
123 IMWRITE_GIF_QUALITY = 1026, //!< For GIF, it can be a quality from 1 to 8. Default is 2. See cv::ImwriteGifCompressionFlags.
124 IMWRITE_GIF_DITHER = 1027, //!< For GIF, it can be a quality from -1(most dither) to 3(no dither). Default is 0.
125 IMWRITE_GIF_TRANSPARENCY = 1028, //!< For GIF, the alpha channel lower than this will be set to transparent. Default is 1.
126 IMWRITE_GIF_COLORTABLE = 1029 //!< For GIF, 0 means global color table is used, 1 means local color table is used. Default is 0.
127};
128
129enum ImwriteJPEGSamplingFactorParams {
130 IMWRITE_JPEG_SAMPLING_FACTOR_411 = 0x411111, //!< 4x1,1x1,1x1
131 IMWRITE_JPEG_SAMPLING_FACTOR_420 = 0x221111, //!< 2x2,1x1,1x1(Default)
132 IMWRITE_JPEG_SAMPLING_FACTOR_422 = 0x211111, //!< 2x1,1x1,1x1
133 IMWRITE_JPEG_SAMPLING_FACTOR_440 = 0x121111, //!< 1x2,1x1,1x1
134 IMWRITE_JPEG_SAMPLING_FACTOR_444 = 0x111111 //!< 1x1,1x1,1x1(No subsampling)
135 };
136
137enum ImwriteTiffCompressionFlags {
138 IMWRITE_TIFF_COMPRESSION_NONE = 1, //!< dump mode
139 IMWRITE_TIFF_COMPRESSION_CCITTRLE = 2, //!< CCITT modified Huffman RLE
140 IMWRITE_TIFF_COMPRESSION_CCITTFAX3 = 3, //!< CCITT Group 3 fax encoding
141 IMWRITE_TIFF_COMPRESSION_CCITT_T4 = 3, //!< CCITT T.4 (TIFF 6 name)
142 IMWRITE_TIFF_COMPRESSION_CCITTFAX4 = 4, //!< CCITT Group 4 fax encoding
143 IMWRITE_TIFF_COMPRESSION_CCITT_T6 = 4, //!< CCITT T.6 (TIFF 6 name)
144 IMWRITE_TIFF_COMPRESSION_LZW = 5, //!< Lempel-Ziv & Welch
145 IMWRITE_TIFF_COMPRESSION_OJPEG = 6, //!< !6.0 JPEG
146 IMWRITE_TIFF_COMPRESSION_JPEG = 7, //!< %JPEG DCT compression
147 IMWRITE_TIFF_COMPRESSION_T85 = 9, //!< !TIFF/FX T.85 JBIG compression
148 IMWRITE_TIFF_COMPRESSION_T43 = 10, //!< !TIFF/FX T.43 colour by layered JBIG compression
149 IMWRITE_TIFF_COMPRESSION_NEXT = 32766, //!< NeXT 2-bit RLE
150 IMWRITE_TIFF_COMPRESSION_CCITTRLEW = 32771, //!< #1 w/ word alignment
151 IMWRITE_TIFF_COMPRESSION_PACKBITS = 32773, //!< Macintosh RLE
152 IMWRITE_TIFF_COMPRESSION_THUNDERSCAN = 32809, //!< ThunderScan RLE
153 IMWRITE_TIFF_COMPRESSION_IT8CTPAD = 32895, //!< IT8 CT w/padding
154 IMWRITE_TIFF_COMPRESSION_IT8LW = 32896, //!< IT8 Linework RLE
155 IMWRITE_TIFF_COMPRESSION_IT8MP = 32897, //!< IT8 Monochrome picture
156 IMWRITE_TIFF_COMPRESSION_IT8BL = 32898, //!< IT8 Binary line art
157 IMWRITE_TIFF_COMPRESSION_PIXARFILM = 32908, //!< Pixar companded 10bit LZW
158 IMWRITE_TIFF_COMPRESSION_PIXARLOG = 32909, //!< Pixar companded 11bit ZIP
159 IMWRITE_TIFF_COMPRESSION_DEFLATE = 32946, //!< Deflate compression, legacy tag
160 IMWRITE_TIFF_COMPRESSION_ADOBE_DEFLATE = 8, //!< Deflate compression, as recognized by Adobe
161 IMWRITE_TIFF_COMPRESSION_DCS = 32947, //!< Kodak DCS encoding
162 IMWRITE_TIFF_COMPRESSION_JBIG = 34661, //!< ISO JBIG
163 IMWRITE_TIFF_COMPRESSION_SGILOG = 34676, //!< SGI Log Luminance RLE
164 IMWRITE_TIFF_COMPRESSION_SGILOG24 = 34677, //!< SGI Log 24-bit packed
165 IMWRITE_TIFF_COMPRESSION_JP2000 = 34712, //!< Leadtools JPEG2000
166 IMWRITE_TIFF_COMPRESSION_LERC = 34887, //!< ESRI Lerc codec: https://github.com/Esri/lerc
167 IMWRITE_TIFF_COMPRESSION_LZMA = 34925, //!< LZMA2
168 IMWRITE_TIFF_COMPRESSION_ZSTD = 50000, //!< ZSTD: WARNING not registered in Adobe-maintained registry
169 IMWRITE_TIFF_COMPRESSION_WEBP = 50001, //!< WEBP: WARNING not registered in Adobe-maintained registry
170 IMWRITE_TIFF_COMPRESSION_JXL = 50002 //!< JPEGXL: WARNING not registered in Adobe-maintained registry
171};
172
173enum ImwriteTiffPredictorFlags {
174 IMWRITE_TIFF_PREDICTOR_NONE = 1, //!< no prediction scheme used
175 IMWRITE_TIFF_PREDICTOR_HORIZONTAL = 2, //!< horizontal differencing
176 IMWRITE_TIFF_PREDICTOR_FLOATINGPOINT = 3 //!< floating point predictor
177
178};
179
180enum ImwriteEXRTypeFlags {
181 /*IMWRITE_EXR_TYPE_UNIT = 0, //!< not supported */
182 IMWRITE_EXR_TYPE_HALF = 1, //!< store as HALF (FP16)
183 IMWRITE_EXR_TYPE_FLOAT = 2 //!< store as FP32 (default)
184 };
185
186enum ImwriteEXRCompressionFlags {
187 IMWRITE_EXR_COMPRESSION_NO = 0, //!< no compression
188 IMWRITE_EXR_COMPRESSION_RLE = 1, //!< run length encoding
189 IMWRITE_EXR_COMPRESSION_ZIPS = 2, //!< zlib compression, one scan line at a time
190 IMWRITE_EXR_COMPRESSION_ZIP = 3, //!< zlib compression, in blocks of 16 scan lines
191 IMWRITE_EXR_COMPRESSION_PIZ = 4, //!< piz-based wavelet compression
192 IMWRITE_EXR_COMPRESSION_PXR24 = 5, //!< lossy 24-bit float compression
193 IMWRITE_EXR_COMPRESSION_B44 = 6, //!< lossy 4-by-4 pixel block compression, fixed compression rate
194 IMWRITE_EXR_COMPRESSION_B44A = 7, //!< lossy 4-by-4 pixel block compression, flat fields are compressed more
195 IMWRITE_EXR_COMPRESSION_DWAA = 8, //!< lossy DCT based compression, in blocks of 32 scanlines. More efficient for partial buffer access. Supported since OpenEXR 2.2.0.
196 IMWRITE_EXR_COMPRESSION_DWAB = 9, //!< lossy DCT based compression, in blocks of 256 scanlines. More efficient space wise and faster to decode full frames than DWAA_COMPRESSION. Supported since OpenEXR 2.2.0.
197 };
198
199//! Imwrite PNG specific flags used to tune the compression algorithm.
200/** These flags will be modify the way of PNG image compression and will be passed to the underlying zlib processing stage.
201
202- The effect of IMWRITE_PNG_STRATEGY_FILTERED is to force more Huffman coding and less string matching; it is somewhat intermediate between IMWRITE_PNG_STRATEGY_DEFAULT and IMWRITE_PNG_STRATEGY_HUFFMAN_ONLY.
203- IMWRITE_PNG_STRATEGY_RLE is designed to be almost as fast as IMWRITE_PNG_STRATEGY_HUFFMAN_ONLY, but give better compression for PNG image data.
204- The strategy parameter only affects the compression ratio but not the correctness of the compressed output even if it is not set appropriately.
205- IMWRITE_PNG_STRATEGY_FIXED prevents the use of dynamic Huffman codes, allowing for a simpler decoder for special applications.
206*/
207enum ImwritePNGFlags {
208 IMWRITE_PNG_STRATEGY_DEFAULT = 0, //!< Use this value for normal data.
209 IMWRITE_PNG_STRATEGY_FILTERED = 1, //!< Use this value for data produced by a filter (or predictor).Filtered data consists mostly of small values with a somewhat random distribution. In this case, the compression algorithm is tuned to compress them better.
210 IMWRITE_PNG_STRATEGY_HUFFMAN_ONLY = 2, //!< Use this value to force Huffman encoding only (no string match).
211 IMWRITE_PNG_STRATEGY_RLE = 3, //!< Use this value to limit match distances to one (run-length encoding).
212 IMWRITE_PNG_STRATEGY_FIXED = 4 //!< Using this value prevents the use of dynamic Huffman codes, allowing for a simpler decoder for special applications.
213 };
214
215//! Imwrite PNG specific values for IMWRITE_PNG_FILTER parameter key
216enum ImwritePNGFilterFlags {
217 IMWRITE_PNG_FILTER_NONE = 8, //!< Applies no filter to the PNG image (useful when you want to save the raw pixel data without any compression filter).
218 IMWRITE_PNG_FILTER_SUB = 16, //!< Applies the "sub" filter, which calculates the difference between the current byte and the previous byte in the row.
219 IMWRITE_PNG_FILTER_UP = 32, //!< applies the "up" filter, which calculates the difference between the current byte and the corresponding byte directly above it.
220 IMWRITE_PNG_FILTER_AVG = 64, //!< applies the "average" filter, which calculates the average of the byte to the left and the byte above.
221 IMWRITE_PNG_FILTER_PAETH = 128, //!< applies the "Paeth" filter, a more complex filter that predicts the next pixel value based on neighboring pixels.
222 IMWRITE_PNG_FAST_FILTERS = (IMWRITE_PNG_FILTER_NONE | IMWRITE_PNG_FILTER_SUB | IMWRITE_PNG_FILTER_UP), //!< This is a combination of IMWRITE_PNG_FILTER_NONE, IMWRITE_PNG_FILTER_SUB, and IMWRITE_PNG_FILTER_UP, typically used for faster compression.
223 IMWRITE_PNG_ALL_FILTERS = (IMWRITE_PNG_FAST_FILTERS | IMWRITE_PNG_FILTER_AVG | IMWRITE_PNG_FILTER_PAETH) //!< This combines all available filters (NONE, SUB, UP, AVG, and PAETH), which will attempt to apply all of them for the best possible compression.
224 };
225
226//! Imwrite PAM specific tupletype flags used to define the 'TUPLETYPE' field of a PAM file.
227enum ImwritePAMFlags {
228 IMWRITE_PAM_FORMAT_NULL = 0,
229 IMWRITE_PAM_FORMAT_BLACKANDWHITE = 1,
230 IMWRITE_PAM_FORMAT_GRAYSCALE = 2,
231 IMWRITE_PAM_FORMAT_GRAYSCALE_ALPHA = 3,
232 IMWRITE_PAM_FORMAT_RGB = 4,
233 IMWRITE_PAM_FORMAT_RGB_ALPHA = 5
234 };
235
236//! Imwrite HDR specific values for IMWRITE_HDR_COMPRESSION parameter key
237enum ImwriteHDRCompressionFlags {
238 IMWRITE_HDR_COMPRESSION_NONE = 0,
239 IMWRITE_HDR_COMPRESSION_RLE = 1
240};
241
242//! Imwrite GIF specific values for IMWRITE_GIF_QUALITY parameter key, if larger than 3, then its related to the size of the color table.
243enum ImwriteGIFCompressionFlags {
244 IMWRITE_GIF_FAST_NO_DITHER = 1,
245 IMWRITE_GIF_FAST_FLOYD_DITHER = 2,
246 IMWRITE_GIF_COLORTABLE_SIZE_8 = 3,
247 IMWRITE_GIF_COLORTABLE_SIZE_16 = 4,
248 IMWRITE_GIF_COLORTABLE_SIZE_32 = 5,
249 IMWRITE_GIF_COLORTABLE_SIZE_64 = 6,
250 IMWRITE_GIF_COLORTABLE_SIZE_128 = 7,
251 IMWRITE_GIF_COLORTABLE_SIZE_256 = 8
252};
253
254enum ImageMetadataType
255{
256 IMAGE_METADATA_UNKNOWN = -1,
257 IMAGE_METADATA_EXIF = 0,
258 IMAGE_METADATA_XMP = 1,
259 IMAGE_METADATA_ICCP = 2,
260 IMAGE_METADATA_MAX = 2
261};
262
263//! @} imgcodecs_flags
264
265/** @brief Represents an animation with multiple frames.
266The `Animation` struct is designed to store and manage data for animated sequences such as those from animated formats (e.g., GIF, AVIF, APNG, WebP).
267It provides support for looping, background color settings, frame timing, and frame storage.
268*/
269struct CV_EXPORTS_W_SIMPLE Animation
270{
271 //! Number of times the animation should loop. 0 means infinite looping.
272 /*! @note At some file format, when N is set, whether it is displayed N or N+1 times depends on the implementation of the user application. This loop times behaviour has not been documented clearly.
273 * - (GIF) See https://issues.chromium.org/issues/40459899
274 * And animated GIF with loop is extended with the Netscape Application Block(NAB), which it not a part of GIF89a specification. See https://en.wikipedia.org/wiki/GIF#Animated_GIF .
275 * - (WebP) See https://issues.chromium.org/issues/41276895
276 */
277 CV_PROP_RW int loop_count;
278 //! Background color of the animation in BGRA format.
279 CV_PROP_RW Scalar bgcolor;
280 //! Duration for each frame in milliseconds.
281 /*! @note (GIF) Due to file format limitation
282 * - Durations must be multiples of 10 milliseconds. Any provided value will be rounded down to the nearest 10ms (e.g., 88ms → 80ms).
283 * - 0ms(or smaller than expected in user application) duration may cause undefined behavior, e.g. it is handled with default duration.
284 * - Over 65535 * 10 milliseconds duration is not supported.
285 */
286 CV_PROP_RW std::vector<int> durations;
287 //! Vector of frames, where each Mat represents a single frame.
288 CV_PROP_RW std::vector<Mat> frames;
289 //! image that can be used for the format in addition to the animation or if animation is not supported in the reader (like in PNG).
290 CV_PROP_RW Mat still_image;
291
292 /** @brief Constructs an Animation object with optional loop count and background color.
293
294 @param loopCount An integer representing the number of times the animation should loop:
295 - `0` (default) indicates infinite looping, meaning the animation will replay continuously.
296 - Positive values denote finite repeat counts, allowing the animation to play a limited number of times.
297 - If a negative value or a value beyond the maximum of `0xffff` (65535) is provided, it is reset to `0`
298 (infinite looping) to maintain valid bounds.
299
300 @param bgColor A `Scalar` object representing the background color in BGR format:
301 - Defaults to `Scalar()`, indicating an empty color (usually transparent if supported).
302 - This background color provides a solid fill behind frames that have transparency, ensuring a consistent display appearance.
303 */
304 CV_WRAP Animation(int loopCount = 0, Scalar bgColor = Scalar());
305};
306
307/** @brief Loads an image from a file.
308
309@anchor imread
310
311The `imread` function loads an image from the specified file and returns OpenCV matrix. If the image cannot be
312read (because of a missing file, improper permissions, or unsupported/invalid format), the function
313returns an empty matrix.
314
315Currently, the following file formats are supported:
316
317- Windows bitmaps - \*.bmp, \*.dib (always supported)
318- GIF files - \*.gif (always supported)
319- JPEG files - \*.jpeg, \*.jpg, \*.jpe (see the *Note* section)
320- JPEG 2000 files - \*.jp2 (see the *Note* section)
321- Portable Network Graphics - \*.png (see the *Note* section)
322- WebP - \*.webp (see the *Note* section)
323- AVIF - \*.avif (see the *Note* section)
324- Portable image format - \*.pbm, \*.pgm, \*.ppm, \*.pxm, \*.pnm (always supported)
325- PFM files - \*.pfm (see the *Note* section)
326- Sun rasters - \*.sr, \*.ras (always supported)
327- TIFF files - \*.tiff, \*.tif (see the *Note* section)
328- OpenEXR Image files - \*.exr (see the *Note* section)
329- Radiance HDR - \*.hdr, \*.pic (always supported)
330- Raster and Vector geospatial data supported by GDAL (see the *Note* section)
331
332@note
333- The function determines the type of an image by its content, not by the file extension.
334- In the case of color images, the decoded images will have the channels stored in **B G R** order.
335- When using IMREAD_GRAYSCALE, the codec's internal grayscale conversion will be used, if available.
336 Results may differ from the output of cvtColor().
337- On Microsoft Windows\* and Mac OS\*, the codecs shipped with OpenCV (libjpeg, libpng, libtiff,
338 and libjasper) are used by default. So, OpenCV can always read JPEGs, PNGs, and TIFFs. On Mac OS,
339 there is also an option to use native Mac OS image readers. However, beware that currently these
340 native image loaders give images with different pixel values because of the color management embedded
341 into Mac OS.
342- On Linux\*, BSD flavors, and other Unix-like open-source operating systems, OpenCV looks for
343 codecs supplied with the OS. Ensure the relevant packages are installed (including development
344 files, such as "libjpeg-dev" in Debian\* and Ubuntu\*) to get codec support, or turn
345 on the OPENCV_BUILD_3RDPARTY_LIBS flag in CMake.
346- If the *WITH_GDAL* flag is set to true in CMake and @ref IMREAD_LOAD_GDAL is used to load the image,
347 the [GDAL](http://www.gdal.org) driver will be used to decode the image, supporting
348 [Raster](http://www.gdal.org/formats_list.html) and [Vector](http://www.gdal.org/ogr_formats.html) formats.
349- If EXIF information is embedded in the image file, the EXIF orientation will be taken into account,
350 and thus the image will be rotated accordingly unless the flags @ref IMREAD_IGNORE_ORIENTATION
351 or @ref IMREAD_UNCHANGED are passed.
352- Use the IMREAD_UNCHANGED flag to preserve the floating-point values from PFM images.
353- By default, the number of pixels must be less than 2^30. This limit can be changed by setting
354 the environment variable `OPENCV_IO_MAX_IMAGE_PIXELS`. See @ref tutorial_env_reference.
355
356@param filename Name of the file to be loaded.
357@param flags Flag that can take values of `cv::ImreadModes`.
358*/
359CV_EXPORTS_W Mat imread( const String& filename, int flags = IMREAD_COLOR_BGR );
360
361/** @brief Loads an image from a file.
362
363This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts and the return value.
364@param filename Name of file to be loaded.
365@param dst object in which the image will be loaded.
366@param flags Flag that can take values of cv::ImreadModes
367@note
368The image passing through the img parameter can be pre-allocated. The memory is reused if the shape and the type match with the load image.
369 */
370CV_EXPORTS_W void imread( const String& filename, OutputArray dst, int flags = IMREAD_COLOR_BGR );
371
372/** @brief Reads an image from a file together with associated metadata.
373
374The function imreadWithMetadata reads image from the specified file. It does the same thing as imread, but additionally reads metadata if the corresponding file contains any.
375@param filename Name of the file to be loaded.
376@param metadataTypes Output vector with types of metadata chucks returned in metadata, see ImageMetadataType.
377@param metadata Output vector of vectors or vector of matrices to store the retrieved metadata
378@param flags Flag that can take values of cv::ImreadModes
379*/
380CV_EXPORTS_W Mat imreadWithMetadata( const String& filename, CV_OUT std::vector<int>& metadataTypes,
381 OutputArrayOfArrays metadata, int flags = IMREAD_ANYCOLOR);
382
383/** @brief Loads a multi-page image from a file.
384
385The function imreadmulti loads a multi-page image from the specified file into a vector of Mat objects.
386@param filename Name of file to be loaded.
387@param mats A vector of Mat objects holding each page.
388@param flags Flag that can take values of cv::ImreadModes, default with cv::IMREAD_ANYCOLOR.
389@sa cv::imread
390*/
391CV_EXPORTS_W bool imreadmulti(const String& filename, CV_OUT std::vector<Mat>& mats, int flags = IMREAD_ANYCOLOR);
392
393/** @brief Loads images of a multi-page image from a file.
394
395The function imreadmulti loads a specified range from a multi-page image from the specified file into a vector of Mat objects.
396@param filename Name of file to be loaded.
397@param mats A vector of Mat objects holding each page.
398@param start Start index of the image to load
399@param count Count number of images to load
400@param flags Flag that can take values of cv::ImreadModes, default with cv::IMREAD_ANYCOLOR.
401@sa cv::imread
402*/
403CV_EXPORTS_W bool imreadmulti(const String& filename, CV_OUT std::vector<Mat>& mats, int start, int count, int flags = IMREAD_ANYCOLOR);
404
405/** @example samples/cpp/tutorial_code/imgcodecs/animations.cpp
406An example to show usage of cv::imreadanimation and cv::imwriteanimation functions.
407Check @ref tutorial_animations "the corresponding tutorial" for more details
408*/
409
410/** @brief Loads frames from an animated image file into an Animation structure.
411
412The function imreadanimation loads frames from an animated image file (e.g., GIF, AVIF, APNG, WEBP) into the provided Animation struct.
413
414@param filename A string containing the path to the file.
415@param animation A reference to an Animation structure where the loaded frames will be stored. It should be initialized before the function is called.
416@param start The index of the first frame to load. This is optional and defaults to 0.
417@param count The number of frames to load. This is optional and defaults to 32767.
418
419@return Returns true if the file was successfully loaded and frames were extracted; returns false otherwise.
420*/
421CV_EXPORTS_W bool imreadanimation(const String& filename, CV_OUT Animation& animation, int start = 0, int count = INT16_MAX);
422
423/** @brief Loads frames from an animated image buffer into an Animation structure.
424
425The function imdecodeanimation loads frames from an animated image buffer (e.g., GIF, AVIF, APNG, WEBP) into the provided Animation struct.
426
427@param buf A reference to an InputArray containing the image buffer.
428@param animation A reference to an Animation structure where the loaded frames will be stored. It should be initialized before the function is called.
429@param start The index of the first frame to load. This is optional and defaults to 0.
430@param count The number of frames to load. This is optional and defaults to 32767.
431
432@return Returns true if the buffer was successfully loaded and frames were extracted; returns false otherwise.
433*/
434CV_EXPORTS_W bool imdecodeanimation(InputArray buf, CV_OUT Animation& animation, int start = 0, int count = INT16_MAX);
435
436/** @brief Saves an Animation to a specified file.
437
438The function imwriteanimation saves the provided Animation data to the specified file in an animated format.
439Supported formats depend on the implementation and may include formats like GIF, AVIF, APNG, or WEBP.
440
441@param filename The name of the file where the animation will be saved. The file extension determines the format.
442@param animation A constant reference to an Animation struct containing the frames and metadata to be saved.
443@param params Optional format-specific parameters encoded as pairs (paramId_1, paramValue_1, paramId_2, paramValue_2, ...).
444These parameters are used to specify additional options for the encoding process. Refer to `cv::ImwriteFlags` for details on possible parameters.
445
446@return Returns true if the animation was successfully saved; returns false otherwise.
447*/
448CV_EXPORTS_W bool imwriteanimation(const String& filename, const Animation& animation, const std::vector<int>& params = std::vector<int>());
449
450/** @brief Encodes an Animation to a memory buffer.
451
452The function imencodeanimation encodes the provided Animation data into a memory
453buffer in an animated format. Supported formats depend on the implementation and
454may include formats like GIF, AVIF, APNG, or WEBP.
455
456@param ext The file extension that determines the format of the encoded data.
457@param animation A constant reference to an Animation struct containing the
458frames and metadata to be encoded.
459@param buf A reference to a vector of unsigned chars where the encoded data will
460be stored.
461@param params Optional format-specific parameters encoded as pairs (paramId_1,
462paramValue_1, paramId_2, paramValue_2, ...). These parameters are used to
463specify additional options for the encoding process. Refer to `cv::ImwriteFlags`
464for details on possible parameters.
465
466@return Returns true if the animation was successfully encoded; returns false otherwise.
467*/
468CV_EXPORTS_W bool imencodeanimation(const String& ext, const Animation& animation, CV_OUT std::vector<uchar>& buf, const std::vector<int>& params = std::vector<int>());
469
470/** @brief Returns the number of images inside the given file
471
472The function imcount returns the number of pages in a multi-page image (e.g. TIFF), the number of frames in an animation (e.g. AVIF), and 1 otherwise.
473If the image cannot be decoded, 0 is returned.
474@param filename Name of file to be loaded.
475@param flags Flag that can take values of cv::ImreadModes, default with cv::IMREAD_ANYCOLOR.
476@todo when cv::IMREAD_LOAD_GDAL flag used the return value will be 0 or 1 because OpenCV's GDAL decoder doesn't support multi-page reading yet.
477*/
478CV_EXPORTS_W size_t imcount(const String& filename, int flags = IMREAD_ANYCOLOR);
479
480/** @brief Saves an image to a specified file.
481
482The function imwrite saves the image to the specified file. The image format is chosen based on the
483filename extension (see cv::imread for the list of extensions). In general, only 8-bit unsigned (CV_8U)
484single-channel or 3-channel (with 'BGR' channel order) images
485can be saved using this function, with these exceptions:
486
487- With OpenEXR encoder, only 32-bit float (CV_32F) images can be saved.
488 - 8-bit unsigned (CV_8U) images are not supported.
489- With Radiance HDR encoder, non 64-bit float (CV_64F) images can be saved.
490 - All images will be converted to 32-bit float (CV_32F).
491- With JPEG 2000 encoder, 8-bit unsigned (CV_8U) and 16-bit unsigned (CV_16U) images can be saved.
492- With JPEG XL encoder, 8-bit unsigned (CV_8U), 16-bit unsigned (CV_16U) and 32-bit float(CV_32F) images can be saved.
493 - JPEG XL images with an alpha channel can be saved using this function.
494 To achieve this, create an 8-bit 4-channel (CV_8UC4) / 16-bit 4-channel (CV_16UC4) / 32-bit float 4-channel (CV_32FC4) BGRA image, ensuring the alpha channel is the last component.
495 Fully transparent pixels should have an alpha value of 0, while fully opaque pixels should have an alpha value of 255/65535/1.0.
496- With PAM encoder, 8-bit unsigned (CV_8U) and 16-bit unsigned (CV_16U) images can be saved.
497- With PNG encoder, 8-bit unsigned (CV_8U) and 16-bit unsigned (CV_16U) images can be saved.
498 - PNG images with an alpha channel can be saved using this function.
499 To achieve this, create an 8-bit 4-channel (CV_8UC4) / 16-bit 4-channel (CV_16UC4) BGRA image, ensuring the alpha channel is the last component.
500 Fully transparent pixels should have an alpha value of 0, while fully opaque pixels should have an alpha value of 255/65535(see the code sample below).
501- With PGM/PPM encoder, 8-bit unsigned (CV_8U) and 16-bit unsigned (CV_16U) images can be saved.
502- With TIFF encoder, 8-bit unsigned (CV_8U), 8-bit signed (CV_8S),
503 16-bit unsigned (CV_16U), 16-bit signed (CV_16S),
504 32-bit signed (CV_32S),
505 32-bit float (CV_32F) and 64-bit float (CV_64F) images can be saved.
506 - Multiple images (vector of Mat) can be saved in TIFF format (see the code sample below).
507 - 32-bit float 3-channel (CV_32FC3) TIFF images will be saved
508 using the LogLuv high dynamic range encoding (4 bytes per pixel)
509- With GIF encoder, 8-bit unsigned (CV_8U) images can be saved.
510 - GIF images with an alpha channel can be saved using this function.
511 To achieve this, create an 8-bit 4-channel (CV_8UC4) BGRA image, ensuring the alpha channel is the last component.
512 Fully transparent pixels should have an alpha value of 0, while fully opaque pixels should have an alpha value of 255.
513 - 8-bit single-channel images (CV_8UC1) are not supported due to GIF's limitation to indexed color formats.
514
515If the image format is not supported, the image will be converted to 8-bit unsigned (CV_8U) and saved that way.
516
517If the format, depth or channel order is different, use
518Mat::convertTo and cv::cvtColor to convert it before saving. Or, use the universal FileStorage I/O
519functions to save the image to XML or YAML format.
520
521The sample below shows how to create a BGRA image, how to set custom compression parameters and save it to a PNG file.
522It also demonstrates how to save multiple images in a TIFF file:
523@include snippets/imgcodecs_imwrite.cpp
524@param filename Name of the file.
525@param img (Mat or vector of Mat) Image or Images to be saved.
526@param params Format-specific parameters encoded as pairs (paramId_1, paramValue_1, paramId_2, paramValue_2, ... .) see cv::ImwriteFlags
527*/
528CV_EXPORTS_W bool imwrite( const String& filename, InputArray img,
529 const std::vector<int>& params = std::vector<int>());
530
531/** @brief Saves an image to a specified file with metadata
532
533The function imwriteWithMetadata saves the image to the specified file. It does the same thing as imwrite, but additionally writes metadata if the corresponding format supports it.
534@param filename Name of the file. As with imwrite, image format is determined by the file extension.
535@param img (Mat or vector of Mat) Image or Images to be saved.
536@param metadataTypes Vector with types of metadata chucks stored in metadata to write, see ImageMetadataType.
537@param metadata Vector of vectors or vector of matrices with chunks of metadata to store into the file
538@param params Format-specific parameters encoded as pairs (paramId_1, paramValue_1, paramId_2, paramValue_2, ... .) see cv::ImwriteFlags
539*/
540CV_EXPORTS_W bool imwriteWithMetadata( const String& filename, InputArray img,
541 const std::vector<int>& metadataTypes,
542 InputArrayOfArrays& metadata,
543 const std::vector<int>& params = std::vector<int>());
544
545//! @brief multi-image overload for bindings
546CV_WRAP static inline
547bool imwritemulti(const String& filename, InputArrayOfArrays img,
548 const std::vector<int>& params = std::vector<int>())
549{
550 return imwrite(filename, img, params);
551}
552
553/** @brief Reads an image from a buffer in memory.
554
555The function imdecode reads an image from the specified buffer in the memory. If the buffer is too short or
556contains invalid data, the function returns an empty matrix ( Mat::data==NULL ).
557
558See cv::imread for the list of supported formats and flags description.
559
560@note In the case of color images, the decoded images will have the channels stored in **B G R** order.
561@param buf Input array or vector of bytes.
562@param flags The same flags as in cv::imread, see cv::ImreadModes.
563*/
564CV_EXPORTS_W Mat imdecode( InputArray buf, int flags );
565
566/** @brief Reads an image from a buffer in memory together with associated metadata.
567
568The function imdecode reads an image from the specified buffer in the memory. If the buffer is too short or
569contains invalid data, the function returns an empty matrix ( Mat::data==NULL ).
570
571See cv::imread for the list of supported formats and flags description.
572
573@note In the case of color images, the decoded images will have the channels stored in **B G R** order.
574@param buf Input array or vector of bytes.
575@param metadataTypes Output vector with types of metadata chucks returned in metadata, see ImageMetadataType.
576@param metadata Output vector of vectors or vector of matrices to store the retrieved metadata
577@param flags The same flags as in cv::imread, see cv::ImreadModes.
578*/
579CV_EXPORTS_W Mat imdecodeWithMetadata( InputArray buf, CV_OUT std::vector<int>& metadataTypes,
580 OutputArrayOfArrays metadata, int flags = IMREAD_ANYCOLOR );
581
582/** @overload
583@param buf Input array or vector of bytes.
584@param flags The same flags as in cv::imread, see cv::ImreadModes.
585@param dst The optional output placeholder for the decoded matrix. It can save the image
586reallocations when the function is called repeatedly for images of the same size. In case of decoder
587failure the function returns empty cv::Mat object, but does not release user-provided dst buffer.
588*/
589CV_EXPORTS Mat imdecode( InputArray buf, int flags, Mat* dst);
590
591/** @brief Reads a multi-page image from a buffer in memory.
592
593The function imdecodemulti reads a multi-page image from the specified buffer in the memory. If the buffer is too short or
594contains invalid data, the function returns false.
595
596See cv::imreadmulti for the list of supported formats and flags description.
597
598@note In the case of color images, the decoded images will have the channels stored in **B G R** order.
599@param buf Input array or vector of bytes.
600@param flags The same flags as in cv::imread, see cv::ImreadModes.
601@param mats A vector of Mat objects holding each page, if more than one.
602@param range A continuous selection of pages.
603*/
604CV_EXPORTS_W bool imdecodemulti(InputArray buf, int flags, CV_OUT std::vector<Mat>& mats, const cv::Range& range = Range::all());
605
606/** @brief Encodes an image into a memory buffer.
607
608The function imencode compresses the image and stores it in the memory buffer that is resized to fit the
609result. See cv::imwrite for the list of supported formats and flags description.
610
611@param ext File extension that defines the output format. Must include a leading period.
612@param img Image to be compressed.
613@param buf Output buffer resized to fit the compressed image.
614@param params Format-specific parameters. See cv::imwrite and cv::ImwriteFlags.
615*/
616CV_EXPORTS_W bool imencode( const String& ext, InputArray img,
617 CV_OUT std::vector<uchar>& buf,
618 const std::vector<int>& params = std::vector<int>());
619
620/** @brief Encodes an image into a memory buffer.
621
622The function imencode compresses the image and stores it in the memory buffer that is resized to fit the
623result. See cv::imwrite for the list of supported formats and flags description.
624
625@param ext File extension that defines the output format. Must include a leading period.
626@param img Image to be compressed.
627@param metadataTypes Vector with types of metadata chucks stored in metadata to write, see ImageMetadataType.
628@param metadata Vector of vectors or vector of matrices with chunks of metadata to store into the file
629@param buf Output buffer resized to fit the compressed image.
630@param params Format-specific parameters. See cv::imwrite and cv::ImwriteFlags.
631*/
632CV_EXPORTS_W bool imencodeWithMetadata( const String& ext, InputArray img,
633 const std::vector<int>& metadataTypes,
634 InputArrayOfArrays metadata,
635 CV_OUT std::vector<uchar>& buf,
636 const std::vector<int>& params = std::vector<int>());
637
638/** @brief Encodes array of images into a memory buffer.
639
640The function is analog to cv::imencode for in-memory multi-page image compression.
641See cv::imwrite for the list of supported formats and flags description.
642
643@param ext File extension that defines the output format. Must include a leading period.
644@param imgs Vector of images to be written.
645@param buf Output buffer resized to fit the compressed data.
646@param params Format-specific parameters. See cv::imwrite and cv::ImwriteFlags.
647*/
648CV_EXPORTS_W bool imencodemulti( const String& ext, InputArrayOfArrays imgs,
649 CV_OUT std::vector<uchar>& buf,
650 const std::vector<int>& params = std::vector<int>());
651
652/** @brief Checks if the specified image file can be decoded by OpenCV.
653
654The function haveImageReader checks if OpenCV is capable of reading the specified file.
655This can be useful for verifying support for a given image format before attempting to load an image.
656
657@param filename The name of the file to be checked.
658@return true if an image reader for the specified file is available and the file can be opened, false otherwise.
659
660@note The function checks the availability of image codecs that are either built into OpenCV or dynamically loaded.
661It does not load the image codec implementation and decode data, but uses signature check.
662If the file cannot be opened or the format is unsupported, the function will return false.
663
664@sa cv::haveImageWriter, cv::imread, cv::imdecode
665*/
666CV_EXPORTS_W bool haveImageReader( const String& filename );
667
668/** @brief Checks if the specified image file or specified file extension can be encoded by OpenCV.
669
670The function haveImageWriter checks if OpenCV is capable of writing images with the specified file extension.
671This can be useful for verifying support for a given image format before attempting to save an image.
672
673@param filename The name of the file or the file extension (e.g., ".jpg", ".png").
674It is recommended to provide the file extension rather than the full file name.
675@return true if an image writer for the specified extension is available, false otherwise.
676
677@note The function checks the availability of image codecs that are either built into OpenCV or dynamically loaded.
678It does not check for the actual existence of the file but rather the ability to write files of the given type.
679
680@sa cv::haveImageReader, cv::imwrite, cv::imencode
681*/
682CV_EXPORTS_W bool haveImageWriter( const String& filename );
683
684/** @brief To read multi-page images on demand
685
686The ImageCollection class provides iterator API to read multi-page images on demand. Create iterator
687to the collection of the images and iterate over the collection. Decode the necessary page with operator*.
688
689The performance of page decoding is O(1) if collection is increment sequentially. If the user wants to access random page,
690then the time Complexity is O(n) because the collection has to be reinitialized every time in order to go to the correct page.
691However, the intermediate pages are not decoded during the process, so typically it's quite fast.
692This is required because multi-page codecs does not support going backwards.
693After decoding the one page, it is stored inside the collection cache. Hence, trying to get Mat object from already decoded page is O(1).
694If you need memory, you can use .releaseCache() method to release cached index.
695The space complexity is O(n) if all pages are decoded into memory. The user is able to decode and release images on demand.
696*/
697class CV_EXPORTS ImageCollection {
698public:
699 struct CV_EXPORTS iterator {
700 iterator(ImageCollection* col);
701 iterator(ImageCollection* col, int end);
702 Mat& operator*();
703 Mat* operator->();
704 iterator& operator++();
705 iterator operator++(int);
706 friend bool operator== (const iterator& a, const iterator& b) { return a.m_curr == b.m_curr; }
707 friend bool operator!= (const iterator& a, const iterator& b) { return a.m_curr != b.m_curr; }
708
709 private:
710 ImageCollection* m_pCollection;
711 int m_curr;
712 };
713
714 ImageCollection();
715 ImageCollection(const String& filename, int flags);
716 void init(const String& img, int flags);
717 size_t size() const;
718 const Mat& at(int index);
719 const Mat& operator[](int index);
720 void releaseCache(int index);
721 iterator begin();
722 iterator end();
723
724 class Impl;
725 Ptr<Impl> getImpl();
726protected:
727 Ptr<Impl> pImpl;
728};
729
730//! @} imgcodecs
731
732} // cv
733
734#endif //OPENCV_IMGCODECS_HPP
735

source code of opencv/modules/imgcodecs/include/opencv2/imgcodecs.hpp