avfilter/vf_ocr: also export confidence of result

diff --git a/doc/filters.texi b/doc/filters.texi
index 0d062786651128fbf282c9c37687868cf688d711..163ffef13f6213c0ef57b589649d02346beaf220 100644 (file)
--- a/doc/filters.texi
+++ b/doc/filters.texi
@@ -12910,6 +12910,7 @@ Set character blacklist.
 @end table
 
 The filter exports recognized text as the frame metadata @code{lavfi.ocr.text}.
+The filter exports confidence of recognized words as the frame metadata @code{lavfi.ocr.confidence}.
 
 @section ocv
 

diff --git a/libavfilter/vf_ocr.c b/libavfilter/vf_ocr.c
index abfff494387b0a78b538d9a6582495b8d5954926..d5f76059b792bd9848fc23974ca2cba29d74c53f 100644 (file)
--- a/libavfilter/vf_ocr.c
+++ b/libavfilter/vf_ocr.c
@@ -100,11 +100,21 @@ static int filter_frame(AVFilterLink *inlink, AVFrame *in)
     AVFilterLink *outlink = ctx->outputs[0];
     OCRContext *s = ctx->priv;
     char *result;
+    int *confs;
 
     result = TessBaseAPIRect(s->tess, in->data[0], 1,
                              in->linesize[0], 0, 0, in->width, in->height);
+    confs = TessBaseAPIAllWordConfidences(s->tess);
     av_dict_set(metadata, "lavfi.ocr.text", result, 0);
+    for (int i = 0; confs[i] != -1; i++) {
+        char number[256];
+
+        snprintf(number, sizeof(number), "%d ", confs[i]);
+        av_dict_set(metadata, "lavfi.ocr.confidence", number, AV_DICT_APPEND);
+    }
+
     TessDeleteText(result);
+    TessDeleteIntArray(confs);
 
     return ff_filter_frame(outlink, in);
 }