Image processing apparatus, method and program

Abstract

An emotion is decided based on both image and voice data, and then a decorated image or a substitute image is outputted. Further, a segment of voice signal is precisely determined for the analysis of the signal. Emotion analysis is conducted along with operations of extracting constituent elements of an image and continuously monitoring motions of the elements. A period during which no motion of lips is observed and a period during which no voice is inputted are used as a dividing point for voice signal, and an emotion in voice is decided. Furthermore, the result from the analysis of the image data and the result from the analysis of the voice data are weighted to eventually determine the emotion, and a synthesized image or a substitute image corresponding to the emotion is outputted.

Description

technical field [0001] The present invention relates to the field of image processing apparatuses, methods and programs for using image and voice information to decorate images with decorative objects or replace images with substitute images. Background technique [0002] In traditional image decoration systems, such as figure 1 As shown, the operator selects a decorative object from a decorative menu 810 for an original image 800 , and then outputs a decorative object 820 or a replacement image 830 . Also, in conventional systems in which images are analyzed, such as figure 2 As shown, motions of parts such as eyebrows 910 or mouth 911 in the original image 900 are analyzed to obtain emotions, and a decoration image 920 or a substitute image 930 is output. In another traditional system in which speech is analyzed, such as image 3 As shown, a speech segment is cut out from a speech signal to detect emotion, analyze frequency, pitch, intonation, volume, etc., and output ...

AI Technical Summary

Problems solved by technology

[0004] First, when detecting emotions based on images alone, it is difficult to determine emotions if the expression of the person is monotonous, or the image is unclear or cannot be obtained

Second, when detecting emotion based on speech alone, if the speech is expressed exaggeratedly, the emotion is likely to be incorrectly determined

Third, when a voice signal is cut out according to silence (silence), it is possible that the voice signal cannot be cut out properly due to the interference of external voice

There is also the possibility that when the voice signal is cut out based on silence, the voice signal cannot be cut out properly due to the interference of external noise

Images