Image processing apparatus and image processing method
Provided is an image processing apparatus including a segmentation unit configured to segment image data into a plurality of segments to create a plurality of segmented image data, a detection unit configured to execute face detection processing for detecting a face area from image data before being segmented and each of the plurality of segmented image data, a recognition unit configured to execute recognition processing for determining whether the face detected by the detection unit is a face of a registered person, in each of the plurality of segmented image data, and a control unit configured to control whether to cause the recognition unit to execute the recognition processing as to each of the plurality of segmented image data depending on a result of the face detection in the image data before being segmented.
1. An image processing apparatus comprising:
a segmentation unit configured to segment, as to image data which has been input, the input image data being image data of a plurality of frames, image data piece included in each of the plurality of frames into a plurality of segments to create a plurality of segmented image data pieces for each of the plurality of frames;
a detection unit configured to execute, as to the plurality of segmented image data pieces which has been input, face detection processing for detecting a face area from each of the plurality of input segmented image data pieces;
a recognition unit configured to execute recognition processing for determining whether the face detected by the detection unit is a face of a registered person, in each of the plurality of segmented image data pieces which has been input; and
a control unit connected to the detection unit and the recognition unit, and configured to control whether to cause the recognition unit to execute the recognition processing as to each of the plurality of segmented image data pieces,
wherein, in a case where a first area of a first frame included in the plurality of frames satisfies predetermined conditions and a second area of the first frame does not satisfy the predetermined conditions, the control unit causes the recognition unit to execute the recognition processing for segmented image data piece which, among a plurality of segmented image data pieces created from a second frame included in the plurality of frames, corresponds to the first area of the first frame, and causes the detection unit to execute the face detection processing without causing the recognition unit to execute the recognition processing for segmented image data piece which, among the plurality of segmented image data pieces created from the second frame, corresponds to the second area of the first frame, and
wherein the predetermined conditions include a condition that the face area has been detected by the detection unit.
2. The image processing apparatus according to claim 1 ,
wherein the segmentation unit reduces, for each of the plurality of frames, the image data piece included in the frame, and
wherein the detection unit executes the face detection processing on reduced image data piece, which has been input, of the first frame.
3. The image processing apparatus according to claim 2 , wherein the predetermined conditions further includes a condition that a size of a face detected from the reduced image data piece of the first frame is equal to or larger than a threshold.
4. The image processing apparatus according to claim 1 ,
wherein, in a case where the first area of the first frame satisfies the predetermined conditions, the control unit causes the recognition unit to execute the recognition processing and causes the detection unit to execute the face detection processing as to the segmented image data piece which, among the plurality of segmented image data pieces created from the second frame by the segmentation unit, corresponds to the first area of the first image.
5. The image processing apparatus according to claim 1 ,
wherein the predetermined conditions further includes a condition that a ratio of an area of the face area detected by the detection unit as to an area of the plurality of segmented image data pieces is equal to or higher than a threshold.
6. An image processing method comprising:
segmenting, as to image data which has been input, the input image data being image data of a plurality of frames, image data piece included in each of the plurality of frames into a plurality of segments to create a plurality of segmented image data pieces for each of the plurality of frames;
executing face detection processing for detecting a face area from each of the plurality of input segmented image data pieces;
executing, recognition processing for determining whether the detected face is a face of a registered person, in each of the plurality of segmented image data pieces; and
controlling whether the recognition processing is executed as to each of the plurality of segmented image data pieces,
wherein, in a case where a first area of a first frame included in the plurality of frames satisfies predetermined conditions and a second area of the first frame does not satisfy the predetermined condition, the recognition processing is caused to be executed for segmented image data piece which, among a plurality of segmented image data pieces created from a second frame included in the plurality of frames, corresponds to the first area of the first frame, the face detection processing is caused to be executed without causing the recognition processing to execute the recognition processing for segmented image data piece which, among the plurality of segmented image data pieces created from the second frame, corresponds to the second area of the first frame,
wherein the predetermined conditions include a condition that the face area has been detected by the detection processing, and
wherein the method is performed using a computer or processor.