Hand detection method and system, image detection method and system, hand segmentation method, storage medium, and device

An image detector system, comprising a processor, a memory and computer program instructions stored in the memory, wherein the computer program instructions are executed by the processor to perform:

• determining a first starting point in a connected domain in an image to be detected;
• determining n farthest extremum points that are different from the first starting point and are in the connected domain in the image to be detected, wherein an Nth farthest extremum point among the n farthest extremum points is a pixel point which is in the connected domain and which has a maximum geodesic distance from an Nth starting point, an (N+1)th starting point is the Nth farthest extremum point, both n and N are positive integers, and N≤n;
• performing region growing by respectively taking the n farthest extremum points as initial points, so as to acquire n regions in the connected domain;
• and
• determining an available region that satisfies a selection condition by determining whether a relationship between a preset feature of each region among the n regions and a preset feature of the connected domain satisfy the selection condition.

A non-transitory computer readable medium, wherein computer program instructions are stored in the non-transitory computer readable medium and applicable to be loaded by a processor to execute following operations:

• determining a first starting point in a connected domain in an image to be detected;
• determining n farthest extremum points that are different from the first starting point and are in the connected domain in the image to be detected, wherein an Nth farthest extremum point among the n farthest extremum points is a pixel point which is in the connected domain and which has a maximum geodesic distance from an Nth starting point, an (N+1)th starting point is the Nth farthest extremum point, both n and N are positive integers, and N≤n;
• performing region growing by respectively taking the n farthest extremum points as initial points, so as to acquire n regions in the connected domain;
• and
• determining an available region that satisfies a selection condition by determining whether a relationship between a preset feature of each region among the n regions and a preset feature of the connected domain satisfy the selection condition.