21 #include <tesseract/capi.h>
40 #define OFFSET(x) offsetof(OCRContext, x)
41 #define FLAGS AV_OPT_FLAG_VIDEO_PARAM|AV_OPT_FLAG_FILTERING_PARAM
46 {
"whitelist",
"set character whitelist",
OFFSET(whitelist),
AV_OPT_TYPE_STRING, {.str=
"0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ.:;,-+_!?\"'[]{}()<>|/\\=*&%$#@!~"}, 0, 0,
FLAGS },
55 s->
tess = TessBaseAPICreate();
61 if (!TessBaseAPISetVariable(s->
tess,
"tessedit_char_whitelist", s->
whitelist)) {
66 if (!TessBaseAPISetVariable(s->
tess,
"tessedit_char_blacklist", s->
blacklist)) {
106 result = TessBaseAPIRect(s->
tess, in->
data[0], 1,
108 av_dict_set(metadata,
"lavfi.ocr.text", result, 0);
109 TessDeleteText(result);
118 TessBaseAPIEnd(s->
tess);
119 TessBaseAPIDelete(s->
tess);
145 .priv_class = &ocr_class,
This structure describes decoded (raw) audio or video data.
static const AVFilterPad ocr_outputs[]
planar YUV 4:4:4, 24bpp, (1 Cr & Cb sample per 1x1 Y samples)
Main libavfilter public API header.
AVFILTER_DEFINE_CLASS(ocr)
static av_cold int init(AVFilterContext *ctx)
const char * name
Pad name.
int ff_filter_frame(AVFilterLink *link, AVFrame *frame)
Send a frame of data to the next filter.
planar YUV 4:2:0, 20bpp, (1 Cr & Cb sample per 2x2 Y & A samples)
static av_cold void uninit(AVFilterContext *ctx)
planar YUV 4:4:0 full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV440P and setting color_range...
planar YUV 4:2:2, 16bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV422P and setting col...
AVDictionary * metadata
metadata.
static int query_formats(AVFilterContext *ctx)
A filter pad used for either input or output.
A link between two filters.
planar YUV 4:2:2 24bpp, (1 Cr & Cb sample per 2x1 Y & A samples)
#define AV_LOG_ERROR
Something went wrong and cannot losslessly be recovered.
static const AVFilterPad ocr_inputs[]
#define NULL_IF_CONFIG_SMALL(x)
Return NULL if CONFIG_SMALL is true, otherwise the argument without modification. ...
void * priv
private data for use by the filter
#define AV_LOG_DEBUG
Stuff which is only useful for libav* developers.
planar YUV 4:2:2, 16bpp, (1 Cr & Cb sample per 2x1 Y samples)
planar YUV 4:2:0, 12bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV420P and setting col...
static const AVFilterPad outputs[]
static int filter_frame(AVFilterLink *inlink, AVFrame *in)
static const AVFilterPad inputs[]
int linesize[AV_NUM_DATA_POINTERS]
For video, size in bytes of each picture line.
planar YUV 4:4:4 32bpp, (1 Cr & Cb sample per 1x1 Y & A samples)
uint8_t pi<< 24) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_U8, uint8_t,(*(constuint8_t *) pi-0x80)*(1.0f/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_U8, uint8_t,(*(constuint8_t *) pi-0x80)*(1.0/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S16, int16_t,(*(constint16_t *) pi >>8)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S16, int16_t,*(constint16_t *) pi *(1.0f/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S16, int16_t,*(constint16_t *) pi *(1.0/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S32, int32_t,(*(constint32_t *) pi >>24)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S32, int32_t,*(constint32_t *) pi *(1.0f/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S32, int32_t,*(constint32_t *) pi *(1.0/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_FLT, float, av_clip_uint8(lrintf(*(constfloat *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_FLT, float, av_clip_int16(lrintf(*(constfloat *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_FLT, float, av_clipl_int32(llrintf(*(constfloat *) pi *(1U<< 31)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_DBL, double, av_clip_uint8(lrint(*(constdouble *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_DBL, double, av_clip_int16(lrint(*(constdouble *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_DBL, double, av_clipl_int32(llrint(*(constdouble *) pi *(1U<< 31))))#defineSET_CONV_FUNC_GROUP(ofmt, ifmt) staticvoidset_generic_function(AudioConvert *ac){}voidff_audio_convert_free(AudioConvert **ac){if(!*ac) return;ff_dither_free(&(*ac) ->dc);av_freep(ac);}AudioConvert *ff_audio_convert_alloc(AVAudioResampleContext *avr, enumAVSampleFormatout_fmt, enumAVSampleFormatin_fmt, intchannels, intsample_rate, intapply_map){AudioConvert *ac;intin_planar, out_planar;ac=av_mallocz(sizeof(*ac));if(!ac) returnNULL;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);returnNULL;}returnac;}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;}elseif(in_planar) ac->func_type=CONV_FUNC_TYPE_INTERLEAVE;elseac->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);returnac;}intff_audio_convert(AudioConvert *ac, AudioData *out, AudioData *in){intuse_generic=1;intlen=in->nb_samples;intp;if(ac->dc){av_log(ac->avr, AV_LOG_TRACE,"%dsamples-audio_convert:%sto%s(dithered)\n", len, av_get_sample_fmt_name(ac->in_fmt), av_get_sample_fmt_name(ac->out_fmt));returnff_convert_dither(ac-> in
int av_dict_set(AVDictionary **pm, const char *key, const char *value, int flags)
Set the given entry in *pm, overwriting an existing entry.
planar YUV 4:1:0, 9bpp, (1 Cr & Cb sample per 4x4 Y samples)
Describe the class of an AVClass context structure.
const char * name
Filter name.
AVFilterLink ** outputs
array of pointers to output links
static enum AVPixelFormat pix_fmts[]
uint8_t * data[AV_NUM_DATA_POINTERS]
pointer to the picture/channel planes.
planar YUV 4:2:0, 12bpp, (1 Cr & Cb sample per 2x2 Y samples)
static const AVOption ocr_options[]
planar YUV 4:4:4, 24bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV444P and setting col...
planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples)
AVFilterContext * dst
dest filter
planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples) full scale (JPEG), deprecated in favor ...
planar YUV 4:4:0 (1 Cr & Cb sample per 1x2 Y samples)
AVPixelFormat
Pixel format.