From 300df41c30c7767729e51be1d09cda02901f9b16 Mon Sep 17 00:00:00 2001 From: Gerion Entrup Date: Sun, 2 Jun 2024 14:02:53 +0200 Subject: [PATCH] libavfilter/signature_lookup: fix jaccard distance Actually, the jaccard distance is defined as D = 1 - intersect / union. Additionally, the distance value is compared against a constant that must be between 0 and 1, which is not the case here. Both facts together has led to the fact, that the function always returned a matching course signature. To leave the constant intact and to avoid floating point computation, this commit multiplies with 1 << 16 making the constant effectively 9000 / (1<<16) =~ 0.14. Reported-by: Sachin Tilloo Reviewed-by: Sachin Tilloo Tested-by: Sachin Tilloo Signed-off-by: Michael Niedermayer --- libavfilter/signature_lookup.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/libavfilter/signature_lookup.c b/libavfilter/signature_lookup.c index a0ca818a9b..46602874de 100644 --- a/libavfilter/signature_lookup.c +++ b/libavfilter/signature_lookup.c @@ -127,9 +127,10 @@ static int get_jaccarddist(SignatureContext *sc, CoarseSignature *first, CoarseS { int jaccarddist, i, composdist = 0, cwthcount = 0; for (i = 0; i < 5; i++) { - if ((jaccarddist = intersection_word(first->data[i], second->data[i])) > 0) { + if ((jaccarddist = (1 << 16) * intersection_word(first->data[i], second->data[i])) > 0) { jaccarddist /= union_word(first->data[i], second->data[i]); } + jaccarddist = (1 << 16) - jaccarddist; if (jaccarddist >= sc->thworddist) { if (++cwthcount > 2) { /* more than half (5/2) of distances are too wide */