FFmpeg
vf_ocr.c
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2015 Paul B Mahol
3  *
4  * This file is part of FFmpeg.
5  *
6  * FFmpeg is free software; you can redistribute it and/or
7  * modify it under the terms of the GNU Lesser General Public
8  * License as published by the Free Software Foundation; either
9  * version 2.1 of the License, or (at your option) any later version.
10  *
11  * FFmpeg is distributed in the hope that it will be useful,
12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14  * Lesser General Public License for more details.
15  *
16  * You should have received a copy of the GNU Lesser General Public
17  * License along with FFmpeg; if not, write to the Free Software
18  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
19  */
20 
21 #include <tesseract/capi.h>
22 
23 #include "libavutil/opt.h"
24 #include "avfilter.h"
25 #include "formats.h"
26 #include "internal.h"
27 #include "video.h"
28 
29 typedef struct OCRContext {
30  const AVClass *class;
31 
32  char *datapath;
33  char *language;
34  char *whitelist;
35  char *blacklist;
36 
37  TessBaseAPI *tess;
38 } OCRContext;
39 
40 #define OFFSET(x) offsetof(OCRContext, x)
41 #define FLAGS AV_OPT_FLAG_VIDEO_PARAM|AV_OPT_FLAG_FILTERING_PARAM
42 
43 static const AVOption ocr_options[] = {
44  { "datapath", "set datapath", OFFSET(datapath), AV_OPT_TYPE_STRING, {.str=NULL}, 0, 0, FLAGS },
45  { "language", "set language", OFFSET(language), AV_OPT_TYPE_STRING, {.str="eng"}, 0, 0, FLAGS },
46  { "whitelist", "set character whitelist", OFFSET(whitelist), AV_OPT_TYPE_STRING, {.str="0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ.:;,-+_!?\"'[]{}()<>|/\\=*&%$#@!~"}, 0, 0, FLAGS },
47  { "blacklist", "set character blacklist", OFFSET(blacklist), AV_OPT_TYPE_STRING, {.str=""}, 0, 0, FLAGS },
48  { NULL }
49 };
50 
52 {
53  OCRContext *s = ctx->priv;
54 
55  s->tess = TessBaseAPICreate();
56  if (TessBaseAPIInit3(s->tess, s->datapath, s->language) == -1) {
57  av_log(ctx, AV_LOG_ERROR, "failed to init tesseract\n");
58  return AVERROR(EINVAL);
59  }
60 
61  if (!TessBaseAPISetVariable(s->tess, "tessedit_char_whitelist", s->whitelist)) {
62  av_log(ctx, AV_LOG_ERROR, "failed to set whitelist\n");
63  return AVERROR(EINVAL);
64  }
65 
66  if (!TessBaseAPISetVariable(s->tess, "tessedit_char_blacklist", s->blacklist)) {
67  av_log(ctx, AV_LOG_ERROR, "failed to set blacklist\n");
68  return AVERROR(EINVAL);
69  }
70 
71  av_log(ctx, AV_LOG_DEBUG, "Tesseract version: %s\n", TessVersion());
72 
73  return 0;
74 }
75 
77 {
78  static const enum AVPixelFormat pix_fmts[] = {
88  };
89 
90  AVFilterFormats *fmts_list = ff_make_format_list(pix_fmts);
91  if (!fmts_list)
92  return AVERROR(ENOMEM);
93  return ff_set_common_formats(ctx, fmts_list);
94 }
95 
97 {
98  AVDictionary **metadata = &in->metadata;
99  AVFilterContext *ctx = inlink->dst;
100  AVFilterLink *outlink = ctx->outputs[0];
101  OCRContext *s = ctx->priv;
102  char *result;
103  int *confs;
104 
105  result = TessBaseAPIRect(s->tess, in->data[0], 1,
106  in->linesize[0], 0, 0, in->width, in->height);
107  confs = TessBaseAPIAllWordConfidences(s->tess);
108  av_dict_set(metadata, "lavfi.ocr.text", result, 0);
109  for (int i = 0; confs[i] != -1; i++) {
110  char number[256];
111 
112  snprintf(number, sizeof(number), "%d ", confs[i]);
113  av_dict_set(metadata, "lavfi.ocr.confidence", number, AV_DICT_APPEND);
114  }
115 
116  TessDeleteText(result);
117  TessDeleteIntArray(confs);
118 
119  return ff_filter_frame(outlink, in);
120 }
121 
123 {
124  OCRContext *s = ctx->priv;
125 
126  TessBaseAPIEnd(s->tess);
127  TessBaseAPIDelete(s->tess);
128 }
129 
131 
132 static const AVFilterPad ocr_inputs[] = {
133  {
134  .name = "default",
135  .type = AVMEDIA_TYPE_VIDEO,
136  .filter_frame = filter_frame,
137  },
138  { NULL }
139 };
140 
141 static const AVFilterPad ocr_outputs[] = {
142  {
143  .name = "default",
144  .type = AVMEDIA_TYPE_VIDEO,
145  },
146  { NULL }
147 };
148 
150  .name = "ocr",
151  .description = NULL_IF_CONFIG_SMALL("Optical Character Recognition."),
152  .priv_size = sizeof(OCRContext),
153  .priv_class = &ocr_class,
155  .init = init,
156  .uninit = uninit,
157  .inputs = ocr_inputs,
158  .outputs = ocr_outputs,
159 };
#define NULL
Definition: coverity.c:32
This structure describes decoded (raw) audio or video data.
Definition: frame.h:295
static const AVFilterPad ocr_outputs[]
Definition: vf_ocr.c:141
AVOption.
Definition: opt.h:246
planar YUV 4:4:4, 24bpp, (1 Cr & Cb sample per 1x1 Y samples)
Definition: pixfmt.h:71
Main libavfilter public API header.
AVFilter ff_vf_ocr
Definition: vf_ocr.c:149
AVFILTER_DEFINE_CLASS(ocr)
TessBaseAPI * tess
Definition: vf_ocr.c:37
AVFilterFormats * ff_make_format_list(const int *fmts)
Create a list of supported formats.
Definition: formats.c:283
static av_cold int init(AVFilterContext *ctx)
Definition: vf_ocr.c:51
const char * name
Pad name.
Definition: internal.h:60
int ff_filter_frame(AVFilterLink *link, AVFrame *frame)
Send a frame of data to the next filter.
Definition: avfilter.c:1093
planar YUV 4:2:0, 20bpp, (1 Cr & Cb sample per 2x2 Y & A samples)
Definition: pixfmt.h:101
#define FLAGS
Definition: vf_ocr.c:41
#define av_cold
Definition: attributes.h:82
static av_cold void uninit(AVFilterContext *ctx)
Definition: vf_ocr.c:122
AVOptions.
planar YUV 4:4:0 full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV440P and setting color_range...
Definition: pixfmt.h:100
planar YUV 4:2:2, 16bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV422P and setting col...
Definition: pixfmt.h:79
AVDictionary * metadata
metadata.
Definition: frame.h:581
static int query_formats(AVFilterContext *ctx)
Definition: vf_ocr.c:76
#define av_log(a,...)
A filter pad used for either input or output.
Definition: internal.h:54
planar YUV 4:2:2 24bpp, (1 Cr & Cb sample per 2x1 Y & A samples)
Definition: pixfmt.h:176
#define i(width, name, range_min, range_max)
Definition: cbs_h2645.c:259
int width
Definition: frame.h:353
#define AV_LOG_ERROR
Something went wrong and cannot losslessly be recovered.
Definition: log.h:176
int ff_set_common_formats(AVFilterContext *ctx, AVFilterFormats *formats)
A helper for query_formats() which sets all links to the same list of formats.
Definition: formats.c:569
static const AVFilterPad ocr_inputs[]
Definition: vf_ocr.c:132
#define NULL_IF_CONFIG_SMALL(x)
Return NULL if CONFIG_SMALL is true, otherwise the argument without modification. ...
Definition: internal.h:186
void * priv
private data for use by the filter
Definition: avfilter.h:353
#define AV_LOG_DEBUG
Stuff which is only useful for libav* developers.
Definition: log.h:197
char * datapath
Definition: vf_ocr.c:32
planar YUV 4:2:2, 16bpp, (1 Cr & Cb sample per 2x1 Y samples)
Definition: pixfmt.h:70
char * blacklist
Definition: vf_ocr.c:35
planar YUV 4:2:0, 12bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV420P and setting col...
Definition: pixfmt.h:78
AVFormatContext * ctx
Definition: movenc.c:48
#define s(width, name)
Definition: cbs_vp9.c:257
#define AV_DICT_APPEND
If the entry already exists, append to it.
Definition: dict.h:80
static int filter_frame(AVFilterLink *inlink, AVFrame *in)
Definition: vf_ocr.c:96
static const AVFilterPad outputs[]
Definition: af_acontrast.c:203
int linesize[AV_NUM_DATA_POINTERS]
For video, size in bytes of each picture line.
Definition: frame.h:326
planar YUV 4:4:4 32bpp, (1 Cr & Cb sample per 1x1 Y & A samples)
Definition: pixfmt.h:177
these buffered frames must be flushed immediately if a new input produces new the filter must not call request_frame to get more It must just process the frame or queue it The task of requesting more frames is left to the filter s request_frame method or the application If a filter has several inputs
int av_dict_set(AVDictionary **pm, const char *key, const char *value, int flags)
Set the given entry in *pm, overwriting an existing entry.
Definition: dict.c:70
uint8_t pi<< 24) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_U8, uint8_t,(*(const uint8_t *) pi-0x80)*(1.0f/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_U8, uint8_t,(*(const uint8_t *) pi-0x80)*(1.0/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S16, int16_t,(*(const int16_t *) pi >> 8)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S16, int16_t,*(const int16_t *) pi *(1.0f/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S16, int16_t,*(const int16_t *) pi *(1.0/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S32, int32_t,(*(const int32_t *) pi >> 24)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S32, int32_t,*(const int32_t *) pi *(1.0f/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S32, int32_t,*(const int32_t *) pi *(1.0/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_FLT, float, av_clip_uint8(lrintf(*(const float *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_FLT, float, av_clip_int16(lrintf(*(const float *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_FLT, float, av_clipl_int32(llrintf(*(const float *) pi *(1U<< 31)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_DBL, double, av_clip_uint8(lrint(*(const double *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_DBL, double, av_clip_int16(lrint(*(const double *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_DBL, double, av_clipl_int32(llrint(*(const double *) pi *(1U<< 31))))#define SET_CONV_FUNC_GROUP(ofmt, ifmt) static void set_generic_function(AudioConvert *ac){}void ff_audio_convert_free(AudioConvert **ac){if(!*ac) return;ff_dither_free(&(*ac) ->dc);av_freep(ac);}AudioConvert *ff_audio_convert_alloc(AVAudioResampleContext *avr, enum AVSampleFormat out_fmt, enum AVSampleFormat in_fmt, int channels, int sample_rate, int apply_map){AudioConvert *ac;int in_planar, out_planar;ac=av_mallocz(sizeof(*ac));if(!ac) return NULL;ac->avr=avr;ac->out_fmt=out_fmt;ac->in_fmt=in_fmt;ac->channels=channels;ac->apply_map=apply_map;if(avr->dither_method!=AV_RESAMPLE_DITHER_NONE &&av_get_packed_sample_fmt(out_fmt)==AV_SAMPLE_FMT_S16 &&av_get_bytes_per_sample(in_fmt) > 2){ac->dc=ff_dither_alloc(avr, out_fmt, in_fmt, channels, sample_rate, apply_map);if(!ac->dc){av_free(ac);return NULL;}return ac;}in_planar=ff_sample_fmt_is_planar(in_fmt, channels);out_planar=ff_sample_fmt_is_planar(out_fmt, channels);if(in_planar==out_planar){ac->func_type=CONV_FUNC_TYPE_FLAT;ac->planes=in_planar?ac->channels:1;}else if(in_planar) ac->func_type=CONV_FUNC_TYPE_INTERLEAVE;else ac->func_type=CONV_FUNC_TYPE_DEINTERLEAVE;set_generic_function(ac);if(ARCH_AARCH64) ff_audio_convert_init_aarch64(ac);if(ARCH_ARM) ff_audio_convert_init_arm(ac);if(ARCH_X86) ff_audio_convert_init_x86(ac);return ac;}int ff_audio_convert(AudioConvert *ac, AudioData *out, AudioData *in){int use_generic=1;int len=in->nb_samples;int p;if(ac->dc){av_log(ac->avr, AV_LOG_TRACE,"%d samples - audio_convert: %s to %s (dithered)\n", len, av_get_sample_fmt_name(ac->in_fmt), av_get_sample_fmt_name(ac->out_fmt));return ff_convert_dither(ac-> in
planar YUV 4:1:0, 9bpp, (1 Cr & Cb sample per 4x4 Y samples)
Definition: pixfmt.h:72
Describe the class of an AVClass context structure.
Definition: log.h:67
Filter definition.
Definition: avfilter.h:144
char * language
Definition: vf_ocr.c:33
const char * name
Filter name.
Definition: avfilter.h:148
#define snprintf
Definition: snprintf.h:34
AVFilterLink ** outputs
array of pointers to output links
Definition: avfilter.h:350
static enum AVPixelFormat pix_fmts[]
Definition: libkvazaar.c:275
uint8_t * data[AV_NUM_DATA_POINTERS]
pointer to the picture/channel planes.
Definition: frame.h:309
The exact code depends on how similar the blocks are and how related they are to the and needs to apply these operations to the correct inlink or outlink if there are several Macros are available to factor that when no extra processing is inlink
planar YUV 4:2:0, 12bpp, (1 Cr & Cb sample per 2x2 Y samples)
Definition: pixfmt.h:66
Y , 8bpp.
Definition: pixfmt.h:74
static const AVOption ocr_options[]
Definition: vf_ocr.c:43
planar YUV 4:4:4, 24bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV444P and setting col...
Definition: pixfmt.h:80
planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples)
Definition: pixfmt.h:73
#define OFFSET(x)
Definition: vf_ocr.c:40
A list of supported formats for one end of a filter link.
Definition: formats.h:64
char * whitelist
Definition: vf_ocr.c:34
planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples) full scale (JPEG), deprecated in favor ...
Definition: pixfmt.h:258
An instance of a filter.
Definition: avfilter.h:338
and forward the result(frame or status change) to the corresponding input.If nothing is possible
int height
Definition: frame.h:353
planar YUV 4:4:0 (1 Cr & Cb sample per 1x2 Y samples)
Definition: pixfmt.h:99
internal API functions
Filter the word “frame” indicates either a video frame or a group of audio as stored in an AVFrame structure Format for each input and each output the list of supported formats For video that means pixel format For audio that means channel sample they are references to shared objects When the negotiation mechanism computes the intersection of the formats supported at each end of a all references to both lists are replaced with a reference to the intersection And when a single format is eventually chosen for a link amongst the remaining all references to the list are updated That means that if a filter requires that its input and output have the same format amongst a supported all it has to do is use a reference to the same list of formats query_formats can leave some formats unset and return AVERROR(EAGAIN) to cause the negotiation mechanism toagain later.That can be used by filters with complex requirements to use the format negotiated on one link to set the formats supported on another.Frame references ownership and permissions
AVPixelFormat
Pixel format.
Definition: pixfmt.h:64