Abstract: A method and a device for recognizing a subject area of an image are provided. The method includes receiving an image to be recognized, and extracting a candidate subject area from the image; eliminating a non-subject area from the extracted candidate subject areas to obtain a target candidate subject area, and adjusting and classifying the target candidate subject areas to obtain at least one set of the target candidate subject areas; and merging the target candidate subject areas in each set of the target candidate subject areas to recognize the subject area of the image.

Abstract: Presented are systems and methods that provide a unified end-to-end detection pipeline for object detection that achieves impressive performance in detecting very small and highly overlapped objects in face and car images. Various embodiments of the present disclosure provide for an accurate and efficient one-stage FCN-based object detector that may be optimized end-to-end during training. Certain embodiments train the object detector on a single scale using jitter-augmentation integrated landmark localization information through joint multi-task learning to improve the performance and accuracy of end-to-end object detection. Various embodiments apply hard negative mining techniques during training to bootstrap detection performance.

Abstract: A method and a device for recognizing a subject area of an image are provided. The method includes receiving an image to be recognized, and extracting a candidate subject area from the image; eliminating a non-subject area from the extracted candidate subject areas to obtain a target candidate subject area, and adjusting and classifying the target candidate subject areas to obtain at least one set of the target candidate subject areas; and merging the target candidate subject areas in each set of the target candidate subject areas to recognize the subject area of the image.

Abstract: Presented are systems and methods that provide a unified end-to-end detection pipeline for object detection that achieves impressive performance in detecting very small and highly overlapped objects in face and car images. Various embodiments of the present disclosure provide for an accurate and efficient one-stage FCN-based object detector that may be optimized end-to-end during training. Certain embodiments train the object detector on a single scale using jitter-augmentation integrated landmark localization information through joint multi-task learning to improve the performance and accuracy of end-to-end object detection. Various embodiments apply hard negative mining techniques during training to bootstrap detection performance.

Abstract: An image identification method and an image identification device are provided. The method comprises acquiring a hand feature region within a sight from a first view by skin color detection; acquiring a feature and a position of a tip of a finger from the hand feature region by performing a pattern recognition for a morphological feature of a stretched hand; recording an interframe displacement of a feature point of the tip of the finger when the tip of the finger delimits a periphery of a target object to obtain a delimiting trajectory from the interframe displacement, closing the delimiting trajectory to form a full-perimeter geometry; projecting the full-perimeter geometry on a plane where a direction of the sight is perpendicular to a plane where the target object is located to obtain a projection region, performing an image identification using the projection region as an identification region of the target object.

Abstract: An image identification method and an image identification device are provided. The method comprises acquiring a hand feature region within a sight from a first view by skin color detection; acquiring a feature and a position of a tip of a finger from the hand feature region by performing a pattern recognition for a morphological feature of a stretched hand; recording an interframe displacement of a feature point of the tip of the finger when the tip of the finger delimits a periphery of a target object to obtain a delimiting trajectory from the interframe displacement, closing the delimiting trajectory to form a full-perimeter geometry; projecting the full-perimeter geometry on a plane where a direction of the sight is perpendicular to a plane where the target object is located to obtain a projection region, performing an image identification using the projection region as an identification region of the target object.