Image processing apparatus, image processing method, and storage medium

An image processing method comprising:

• calculating a first similarity between each pair in a plurality of face image dictionaries corresponding to a plurality of sequences created in such a manner that one sequence includes a plurality of frames with a plurality of consecutive face images included in video image data, and a second similarity between each pair of each face image dictionary and a predetermined plurality of dictionaries;
• correcting the calculated and obtained plurality of first similarities using the second similarities;
• and
• comparing the corrected plurality of first similarities with a predetermined threshold to cluster the plurality of face image dictionaries.

An image processing apparatus comprising:

• a face image detecting section configured to detect face images in each frame included in video image data;
• an inter-frame similarity calculating section configured to calculate inter-frame similarities of two consecutive frames in the video image data;
• a sequence creating section configured to create a plurality of sequences in such a manner that one sequence includes consecutive face images of a same person in the video image data, based on the plurality of face images detected by the face image detecting section and the inter-frame similarities calculated and obtained by the inter-frame similarity calculating section;
• a similarity calculating section configured to calculate a first similarity between each pair in a plurality of face image dictionaries created for each sequence and a second similarity between each pair of each face image dictionary and a predetermined plurality of dictionaries;
• a similarity correcting section configured to correct the calculated and obtained plurality of first similarities using the second similarities;
• and
• a face clustering section configured to compare the plurality of first similarities corrected by the similarity correcting section with a predetermined threshold to cluster the plurality of face image dictionaries.