diff mbox series

[FFmpeg-devel,V3] lavf/vf_ocr: add subregion support

Message ID tencent_B881CD16BB9B15BE156A39F1BC351C8C9407@qq.com
State Superseded
Headers show
Series [FFmpeg-devel,V3] lavf/vf_ocr: add subregion support
Related show

Checks

Context Check Description
andriy/x86_make success Make finished
andriy/x86_make_fate success Make fate finished
andriy/PPC64_make success Make finished
andriy/PPC64_make_fate success Make fate finished

Commit Message

Lingjiang Fang June 18, 2021, 3:56 p.m. UTC
fix doc errors, ping for review, thanks :)
---
 doc/filters.texi     |  8 ++++++++
 libavfilter/vf_ocr.c | 35 ++++++++++++++++++++++++++++++++++-
 2 files changed, 42 insertions(+), 1 deletion(-)

Comments

Lingjiang Fang July 5, 2021, 6:54 a.m. UTC | #1
On Fri, 18 Jun 2021 23:56:56 +0800
Lingjiang Fang <vacingfang@foxmail.com> wrote:

ping for review, thanks 

> fix doc errors, ping for review, thanks :)
> ---
>  doc/filters.texi     |  8 ++++++++
>  libavfilter/vf_ocr.c | 35 ++++++++++++++++++++++++++++++++++-
>  2 files changed, 42 insertions(+), 1 deletion(-)
> 
> diff --git a/doc/filters.texi b/doc/filters.texi
> index da8f7d7726..041fd28c57 100644
> --- a/doc/filters.texi
> +++ b/doc/filters.texi
> @@ -15451,6 +15451,14 @@ Set character whitelist.
>  
>  @item blacklist
>  Set character blacklist.
> +
> +@item x, y
> +Set top-left corner of the subregion, in pixels, default is (0,0).
> +
> +@item w, h
> +Set width and height of the subregion, in pixels,
> +default is the bottom-right part from given top-left corner.
> +
>  @end table
>  
>  The filter exports recognized text as the frame metadata
> @code{lavfi.ocr.text}. diff --git a/libavfilter/vf_ocr.c
> b/libavfilter/vf_ocr.c index 6de474025a..e96dce2d87 100644
> --- a/libavfilter/vf_ocr.c
> +++ b/libavfilter/vf_ocr.c
> @@ -33,6 +33,8 @@ typedef struct OCRContext {
>      char *language;
>      char *whitelist;
>      char *blacklist;
> +    int x, y;
> +    int w, h;
>  
>      TessBaseAPI *tess;
>  } OCRContext;
> @@ -45,6 +47,10 @@ static const AVOption ocr_options[] = {
>      { "language",  "set language",            OFFSET(language),
> AV_OPT_TYPE_STRING, {.str="eng"}, 0, 0, FLAGS }, { "whitelist", "set
> character whitelist", OFFSET(whitelist), AV_OPT_TYPE_STRING,
> {.str="0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ.:;,-+_!?\"'[]{}()<>|/\\=*&%$#@!~
> "}, 0, 0, FLAGS }, { "blacklist", "set character blacklist",
> OFFSET(blacklist), AV_OPT_TYPE_STRING, {.str=""},    0, 0, FLAGS },
> +    { "x",         "top x of sub region",     OFFSET(x),
> AV_OPT_TYPE_INT,    {.i64=0},     0, INT_MAX, FLAGS },
> +    { "y",         "top y of sub region",     OFFSET(y),
> AV_OPT_TYPE_INT,    {.i64=0},     0, INT_MAX, FLAGS },
> +    { "w",         "width of sub region",     OFFSET(w),
> AV_OPT_TYPE_INT,    {.i64=0},     0, INT_MAX, FLAGS },
> +    { "h",         "height of sub region",    OFFSET(h),
> AV_OPT_TYPE_INT,    {.i64=0},     0, INT_MAX, FLAGS }, { NULL }
>  };
>  
> @@ -93,6 +99,21 @@ static int query_formats(AVFilterContext *ctx)
>      return ff_set_common_formats(ctx, fmts_list);
>  }
>  
> +static void check_fix(int *x, int *y, int *w, int *h, int pic_w, int
> pic_h) +{
> +    // 0 <= x < pic_w
> +    if (*x >= pic_w)
> +        *x = 0;
> +    // 0 <= y < pic_h
> +    if (*y >= pic_h)
> +        *y = 0;
> +
> +    if (*w == 0 || *w + *x > pic_w)
> +        *w = pic_w - *x;
> +    if (*h == 0 || *h + *y > pic_h)
> +        *h = pic_h - *y;
> +}
> +
>  static int filter_frame(AVFilterLink *inlink, AVFrame *in)
>  {
>      AVDictionary **metadata = &in->metadata;
> @@ -102,8 +123,20 @@ static int filter_frame(AVFilterLink *inlink,
> AVFrame *in) char *result;
>      int *confs;
>  
> +    // TODO(vacing): support expression
> +    int x = s->x;
> +    int y = s->y;
> +    int w = s->w;
> +    int h = s->h;
> +    check_fix(&x, &y, &w, &h, in->width, in->height);
> +    if ( x != s->x || y != s->y  ||
> +        (s->w != 0 && w != s->w) || (s->h != 0 && h != s->h)) {
> +        av_log(s, AV_LOG_WARNING, "config error, subregion changed
> to x=%d, y=%d, w=%d, h=%d\n",
> +
> x, y, w, h);
> +    }
> +
>      result = TessBaseAPIRect(s->tess, in->data[0], 1,
> -                             in->linesize[0], 0, 0, in->width,
> in->height);
> +                             in->linesize[0], x, y, w, h);
>      confs = TessBaseAPIAllWordConfidences(s->tess);
>      av_dict_set(metadata, "lavfi.ocr.text", result, 0);
>      for (int i = 0; confs[i] != -1; i++) {



Regards,
Lingjiang Fang
Steven Liu July 5, 2021, 11:41 a.m. UTC | #2
> 2021年6月18日 下午11:56,Lingjiang Fang <vacingfang@foxmail.com> 写道:
> 
> 
> fix doc errors, ping for review, thanks :)
> ---
> doc/filters.texi     |  8 ++++++++
> libavfilter/vf_ocr.c | 35 ++++++++++++++++++++++++++++++++++-
> 2 files changed, 42 insertions(+), 1 deletion(-)
> 
> diff --git a/doc/filters.texi b/doc/filters.texi
> index da8f7d7726..041fd28c57 100644
> --- a/doc/filters.texi
> +++ b/doc/filters.texi
> @@ -15451,6 +15451,14 @@ Set character whitelist.
> 
> @item blacklist
> Set character blacklist.
> +
> +@item x, y
> +Set top-left corner of the subregion, in pixels, default is (0,0).
> +
> +@item w, h
> +Set width and height of the subregion, in pixels,
> +default is the bottom-right part from given top-left corner.
> +
> @end table
> 
> The filter exports recognized text as the frame metadata @code{lavfi.ocr.text}.
> diff --git a/libavfilter/vf_ocr.c b/libavfilter/vf_ocr.c
> index 6de474025a..e96dce2d87 100644
> --- a/libavfilter/vf_ocr.c
> +++ b/libavfilter/vf_ocr.c
> @@ -33,6 +33,8 @@ typedef struct OCRContext {
>     char *language;
>     char *whitelist;
>     char *blacklist;
> +    int x, y;
> +    int w, h;
> 
>     TessBaseAPI *tess;
> } OCRContext;
> @@ -45,6 +47,10 @@ static const AVOption ocr_options[] = {
>     { "language",  "set language",            OFFSET(language),  AV_OPT_TYPE_STRING, {.str="eng"}, 0, 0, FLAGS },
>     { "whitelist", "set character whitelist", OFFSET(whitelist), AV_OPT_TYPE_STRING, {.str="0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ.:;,-+_!?\"'[]{}()<>|/\\=*&%$#@!~ "}, 0, 0, FLAGS },
>     { "blacklist", "set character blacklist", OFFSET(blacklist), AV_OPT_TYPE_STRING, {.str=""},    0, 0, FLAGS },
> +    { "x",         "top x of sub region",     OFFSET(x),         AV_OPT_TYPE_INT,    {.i64=0},     0, INT_MAX, FLAGS },
> +    { "y",         "top y of sub region",     OFFSET(y),         AV_OPT_TYPE_INT,    {.i64=0},     0, INT_MAX, FLAGS },
> +    { "w",         "width of sub region",     OFFSET(w),         AV_OPT_TYPE_INT,    {.i64=0},     0, INT_MAX, FLAGS },
> +    { "h",         "height of sub region",    OFFSET(h),         AV_OPT_TYPE_INT,    {.i64=0},     0, INT_MAX, FLAGS },
>     { NULL }
> };
> 
> @@ -93,6 +99,21 @@ static int query_formats(AVFilterContext *ctx)
>     return ff_set_common_formats(ctx, fmts_list);
> }
> 
> +static void check_fix(int *x, int *y, int *w, int *h, int pic_w, int pic_h)
> +{
> +    // 0 <= x < pic_w
> +    if (*x >= pic_w)
> +        *x = 0;
> +    // 0 <= y < pic_h
> +    if (*y >= pic_h)
> +        *y = 0;
> +
> +    if (*w == 0 || *w + *x > pic_w)
> +        *w = pic_w - *x;
> +    if (*h == 0 || *h + *y > pic_h)
> +        *h = pic_h - *y;
> +}

What about check whether the logo area fits in the frame when .config_props = config_input ?
> +
> static int filter_frame(AVFilterLink *inlink, AVFrame *in)
> {
>     AVDictionary **metadata = &in->metadata;
> @@ -102,8 +123,20 @@ static int filter_frame(AVFilterLink *inlink, AVFrame *in)
>     char *result;
>     int *confs;
> 
> +    // TODO(vacing): support expression
> +    int x = s->x;
> +    int y = s->y;
> +    int w = s->w;
> +    int h = s->h;
> +    check_fix(&x, &y, &w, &h, in->width, in->height);
> +    if ( x != s->x || y != s->y  ||
> +        (s->w != 0 && w != s->w) || (s->h != 0 && h != s->h)) {
> +        av_log(s, AV_LOG_WARNING, "config error, subregion changed to x=%d, y=%d, w=%d, h=%d\n",
> +                                                                    x, y, w, h);
> +    }
> +
>     result = TessBaseAPIRect(s->tess, in->data[0], 1,
> -                             in->linesize[0], 0, 0, in->width, in->height);
> +                             in->linesize[0], x, y, w, h);
>     confs = TessBaseAPIAllWordConfidences(s->tess);
>     av_dict_set(metadata, "lavfi.ocr.text", result, 0);
>     for (int i = 0; confs[i] != -1; i++) {
> -- 
> 2.29.2
> 
> _______________________________________________
> ffmpeg-devel mailing list
> ffmpeg-devel@ffmpeg.org
> https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
> 
> To unsubscribe, visit link above, or email
> ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
> 

Thanks

Steven Liu
diff mbox series

Patch

diff --git a/doc/filters.texi b/doc/filters.texi
index da8f7d7726..041fd28c57 100644
--- a/doc/filters.texi
+++ b/doc/filters.texi
@@ -15451,6 +15451,14 @@  Set character whitelist.
 
 @item blacklist
 Set character blacklist.
+
+@item x, y
+Set top-left corner of the subregion, in pixels, default is (0,0).
+
+@item w, h
+Set width and height of the subregion, in pixels,
+default is the bottom-right part from given top-left corner.
+
 @end table
 
 The filter exports recognized text as the frame metadata @code{lavfi.ocr.text}.
diff --git a/libavfilter/vf_ocr.c b/libavfilter/vf_ocr.c
index 6de474025a..e96dce2d87 100644
--- a/libavfilter/vf_ocr.c
+++ b/libavfilter/vf_ocr.c
@@ -33,6 +33,8 @@  typedef struct OCRContext {
     char *language;
     char *whitelist;
     char *blacklist;
+    int x, y;
+    int w, h;
 
     TessBaseAPI *tess;
 } OCRContext;
@@ -45,6 +47,10 @@  static const AVOption ocr_options[] = {
     { "language",  "set language",            OFFSET(language),  AV_OPT_TYPE_STRING, {.str="eng"}, 0, 0, FLAGS },
     { "whitelist", "set character whitelist", OFFSET(whitelist), AV_OPT_TYPE_STRING, {.str="0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ.:;,-+_!?\"'[]{}()<>|/\\=*&%$#@!~ "}, 0, 0, FLAGS },
     { "blacklist", "set character blacklist", OFFSET(blacklist), AV_OPT_TYPE_STRING, {.str=""},    0, 0, FLAGS },
+    { "x",         "top x of sub region",     OFFSET(x),         AV_OPT_TYPE_INT,    {.i64=0},     0, INT_MAX, FLAGS },
+    { "y",         "top y of sub region",     OFFSET(y),         AV_OPT_TYPE_INT,    {.i64=0},     0, INT_MAX, FLAGS },
+    { "w",         "width of sub region",     OFFSET(w),         AV_OPT_TYPE_INT,    {.i64=0},     0, INT_MAX, FLAGS },
+    { "h",         "height of sub region",    OFFSET(h),         AV_OPT_TYPE_INT,    {.i64=0},     0, INT_MAX, FLAGS },
     { NULL }
 };
 
@@ -93,6 +99,21 @@  static int query_formats(AVFilterContext *ctx)
     return ff_set_common_formats(ctx, fmts_list);
 }
 
+static void check_fix(int *x, int *y, int *w, int *h, int pic_w, int pic_h)
+{
+    // 0 <= x < pic_w
+    if (*x >= pic_w)
+        *x = 0;
+    // 0 <= y < pic_h
+    if (*y >= pic_h)
+        *y = 0;
+
+    if (*w == 0 || *w + *x > pic_w)
+        *w = pic_w - *x;
+    if (*h == 0 || *h + *y > pic_h)
+        *h = pic_h - *y;
+}
+
 static int filter_frame(AVFilterLink *inlink, AVFrame *in)
 {
     AVDictionary **metadata = &in->metadata;
@@ -102,8 +123,20 @@  static int filter_frame(AVFilterLink *inlink, AVFrame *in)
     char *result;
     int *confs;
 
+    // TODO(vacing): support expression
+    int x = s->x;
+    int y = s->y;
+    int w = s->w;
+    int h = s->h;
+    check_fix(&x, &y, &w, &h, in->width, in->height);
+    if ( x != s->x || y != s->y  ||
+        (s->w != 0 && w != s->w) || (s->h != 0 && h != s->h)) {
+        av_log(s, AV_LOG_WARNING, "config error, subregion changed to x=%d, y=%d, w=%d, h=%d\n",
+                                                                    x, y, w, h);
+    }
+
     result = TessBaseAPIRect(s->tess, in->data[0], 1,
-                             in->linesize[0], 0, 0, in->width, in->height);
+                             in->linesize[0], x, y, w, h);
     confs = TessBaseAPIAllWordConfidences(s->tess);
     av_dict_set(metadata, "lavfi.ocr.text", result, 0);
     for (int i = 0; confs[i] != -1; i++) {