Close-range gesture recognition method based on morphology
A technology based on morphology and gesture recognition, applied in the field of close-range gesture recognition based on morphology, can solve problems such as difficult recognition of merging fingers
Active Publication Date: 2018-11-23
XIAMEN UNIV
View PDF9 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This method involves an effective and reasonable coordinate elimination mechanism in the process of recognizing the hand area, including a new type of scientific image convolution operator, which is invariant to rotation and can quickly recognize complex gestures in the near view. Strong filtering ability, which solves the difficulty of identifying and merging fingers with existing algorithms
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0081] The specific implementation method of the coordinate elimination mechanism proposed by the present invention will be described in detail below.
[0082] see figure 1 , where A is the RGB color original image; B is the hand mask box1 in the RGB color original image; C is the hand mask box2 after RGBD registration between the RGB color original image and the depth image; D is the hand mask box2 is the hand mask box3 after the background is removed; E is the down-sampled image of the hand mask box3; F is the preliminary finger-end image extracted according to the voting mechanism; G is the finger-end image accurately extracted after opening operation; H is the stretched finger index N; I is the classification model; J is the gesture type. combine figure 1 Describe the gesture recognition method proposed by the present invention, and the specific implementation steps are as follows:
[0083] Step 1, obtain the hand mask: shoot the picture containing the hand, collect th...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention aims to provide a close-range gesture recognition method based on morphology. The method comprises the following steps: first, acquiring an RGB color image and a depth image, and acquiring a hand mask box1 in the color image by using a haar feature detector; acquiring an RGBD image of the hand region after segmentation according to the RGBD alignment principle, the first-order difference and the threshold processing in sequence; cutting the region of interest ROI to acquire a hand mask box3; solving the maximum inscribed circle for the hand mask box3, and estimating palm size andpalm center position by geometric parameters of the inscribed circle; designing a coordinate elimination mechanism to extract fingertip regions and a fingertip number N, and selecting a CNN classification model trained in advance according to the value of N; and classifying gestures to acquire a final gesture type. In the process of recognizing the hand region, the close-range gesture recognitionmethod specially designs a coordinate elimination mechanism and a new scientific image convolution operator, which has rotation invariance and can quickly recognize complex gestures in close range.
Description
technical field [0001] The present invention relates to algorithms for gesture recognition. More specifically, it is a method of close-range gesture recognition based on morphology, and a specific method to realize this method to accelerate the calculation is proposed. Background technique [0002] With the wide application of computers, human-computer interaction has become an important part of people's daily life. The ultimate goal of human-computer interaction is to realize natural communication between humans and machines, so gesture recognition research conforms to the needs of people's life development. At present, gesture recognition has also been applied in various fields, such as live video, robotics and AR. However, due to the diversity, ambiguity, and differences in time and space of gestures, as well as the complexity of the human hand and the ill-posedness of vision itself, gesture recognition has become a multidisciplinary research topic. [0003] There are ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06N3/04
CPCG06V40/107G06V40/28G06V40/117G06N3/045
Inventor 殷春平王德鑫廖采莹董一巍尤延铖
Owner XIAMEN UNIV