Image processing apparatus and image processing method
An area where a specific object is captured is extracted as a specific area from the image of a frame of interest, and the evaluation value of the specific area is obtained using a predetermined evaluation formula. It is determined whether the evaluation value of the specific area in a frame preceding the frame of interest has exceeded a predetermined threshold. When it is determined that the evaluation value of the specific area has exceeded the predetermined threshold, the frame of interest is encoded to set the code amount of the specific area in the image of the frame of interest to be smaller than that of the specific area in the image of the frame preceding the frame of interest.
1. An image processing apparatus which encodes respective frames that form a moving image, comprising:
an extraction unit configured to extract a specific area from a frame based on an object appearing in the frame;
an evaluation unit configured to obtain an evaluation value of the specific area;
a determination unit configured to determine, on the basis of the evaluation value of the specific area in a preceding frame preceding the frame, an encoding parameter being used for encoding the specific area in the frame so that a code amount of the specific area in the frame is smaller than a code amount of the specific area in the preceding frame in a case where the evaluation values of the specific areas in the frame and preceding frame exceed a predetermined threshold, wherein an object which is detected from the frame for extracting the specific area from the frame corresponds to an object which is detected from the preceding frame for extracting the specific area from the preceding frame; and
an encoding unit configured to encode the specific area in the frame on the basis of the encoding parameter which is determined by said determination unit for the frame.
2. The apparatus according to claim 1 , wherein said evaluation unit obtains a higher evaluation value in a case where the specific area has a first size in comparison with a case where the specific area has a second size being smaller than the first size.
3. A non-transitory computer-readable storage medium storing a computer program for causing a computer to function as each unit of an image processing apparatus defined in claim 2 .
4. The apparatus according to claim 1 , wherein said evaluation unit obtains the evaluation value, the evaluation value being based on a direction of a face being detected as the object.
5. The apparatus according to claim 1 , wherein said evaluation unit obtains a higher evaluation value in a case where a block distortion amount of the specific area is a first amount in comparison with a case where the block distortion amount of the specific area is a second amount being larger than the first amount.
6. The apparatus according to claim 1 , wherein said evaluation unit acquires importance of the object in the specific area, and obtains a higher evaluation value in a case where the importance of the object is a first importance in comparison with a case where the importance of the object is a second importance being higher than the first importance.
7. A non-transitory computer-readable storage medium storing a computer program for causing a computer to function as each unit of an image processing apparatus defined in claim 1 .
8. The apparatus according to claim 1 , wherein said determination unit determines the encoding parameter for the frame on the basis of the evaluation value of the specific area in the frame and the evaluation values of the specific areas in a predetermined number of preceding frames, wherein an object which is detected from the frame for extracting the specific area from the frame corresponds to objects which are detected from the preceding frames for extracting the specific areas from the preceding frames.
9. An image processing method to be performed by an image processing apparatus which encodes respective frames that form a moving image, comprising:
an extraction step configured to extract a specific area from a frame based on an object appearing in the frame;
an evaluation step configured to obtain an evaluation value of the specific area;
a determination step configured to determine, on the basis of the evaluation value of the specific area in a preceding frame preceding the frame, an encoding parameter being used for encoding the specific area in the frame so that a code amount of the specific area in the frame is smaller than a code amount of the specific area in the preceding frame in a case where the evaluation values of the specific areas in the frame and preceding frame exceed a predetermined threshold, wherein an object which is detected from the frame for extracting the specific area from the frame corresponds to an object which is detected from the preceding frame for extracting the specific area from the preceding frame; and
an encoding step configured to encode the specific area in the frame on the basis of the encoding parameter which is determined by said determination unit for the frame.
10. The image processing method according to claim 9 , wherein said evaluation step obtains a higher evaluation value in a case where the specific area has a first size in comparison with a case where the specific area has a second size being smaller than the first size.