Multi-area employee number detection method applied to company management
A company management and detection method technology, which is applied in the direction of nuclear methods, instruments, character and pattern recognition, etc., can solve the problems of low practicability of the distribution index of the number of employees in the region, and the low accuracy of the detection of the number of employees, so as to improve the accuracy and robustness performance, improving accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0047] see figure 1 , figure 1 Shown is a step diagram of a multi-region employee number detection method applied to company management provided by the embodiment of the present application.
[0048] The embodiment of the present application provides a method for detecting the number of employees in multiple regions applied to company management, including the following steps:
[0049] Select the face image of the employee as a positive sample, and select a non-face image as a negative sample;
[0050] Train positive samples and negative samples to obtain a face detection decision model;
[0051] Extract the images of each area of the company according to the preset time period;
[0052] Use the face detection decision model to detect the face of each area image, and distinguish each area image into a face area, a potential face area and a non-face area;
[0053] Perform secondary detection on the potential face area to screen out the face area;
[0054] Record and count ...
Embodiment approach
[0058] As a preferred embodiment, it also includes:
[0059] Significance detection is performed on the positive sample, and it is judged whether the significance of the positive sample is obvious, and if not, the positive sample is marked.
[0060] Among them, the saliency detection of the positive samples can mark the non-significant positive samples, that is, the positive samples that may be side faces or partially occluded face images, so that the non-significant positive samples can be compared with the significant positive samples. Distinguished positive samples and negative samples with obvious sex, and performed different training respectively.
[0061] As a preferred implementation manner, the method adopted for the above-mentioned saliency detection is the FT saliency algorithm.
[0062] Among them, there are three classic models for image saliency detection, including IT model, CA model and FT model. The IT model is an image saliency algorithm model based on the p...
Embodiment 2
[0079] see figure 2 , figure 2 What is shown is a schematic structural block diagram of an electronic device provided in an embodiment of the present application.
[0080] In the second aspect, the embodiment of the present application provides an electronic device, including a memory 101, a processor 102, and a communication interface 103. The memory 101, the processor 102, and the communication interface 103 are electrically connected to each other directly or indirectly, so as to realize Transmission or Interaction of Data. For example, these components can be electrically connected to each other through one or more communication buses or signal lines.
[0081] The memory 101 can be used to store software programs and modules. The processor 102 executes various functional applications and data processing by executing the software programs and modules stored in the memory 101. The communication interface 103 can be used to communicate with other node devices for signalin...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More