High-adaptability identification counting method for multiple fields

Abstract

The invention discloses a high-adaptability identification counting method for multiple fields, which is suitable for counting targets and comprises the following steps of: inputting an to-be-detectedimage; analyzing a to-be-detected region of the to-be-detected image based on gray information and shape information to obtain a target area ROI; extracting array features of a ROI of the target area; judging whether the target is in regular array distribution or not according to the array characteristics, and counting the target according to a judgment result to obtain a counting value of a target. The method can automatically search a target and perform counting operation so as to meet the counting requirements of different fields, does not need repeated development and deployment, is highin adaptability and counting efficiency, can greatly shorten the development period of the counting method, and effectively improves the productivity.

Description

technical field [0001] The invention relates to the technical field of counting methods, in particular to a multi-field-oriented highly adaptable identification and counting method. Background technique [0002] In the fields of biology, medicine, semiconductor, chemical industry, etc., it is often necessary to identify target objects and count their numbers as the basis for subsequent research and production. For example, in the field of biology, the number of cancerous cells in samples can be counted as the basis for judging cancerous changes; in the field of medicine, the number of drugs per unit batch can be calculated to judge the stability of the production line; Perceive the amount of metallographic carbon and judge the performance and quality of metal materials. [0003] The existing identification and counting methods mainly include artificial identification method, photoelectric induction method, biological fusion method, and image processing method. Among them, ...

AI Technical Summary

Problems solved by technology

Among them, the artificial recognition method uses human experience to identify specific targets and count them. It is widely used in various fields. For occasions that focus on experience and do not rely on efficiency, this method is generally used, but it relies heavily on manpower, and the experience is unstable. Large, resulting in poor repetition accuracy and low efficiency; the photoelectric induction method uses photoelectric induction sensors to count, which is more common in industrial assembly lines, and is only suitable for simple indiscriminate counting, and cannot intelligently identify and count target objects; the biological fusion method is more common in the field of biotechnology , using the receptor binding principle in cell engineering to screen target cells and complete identification and counting, but this method is costly, expensive, and destroys the identification object; image processing is an indirect identification method widely used in various fields , non-destructive to the target object, and can take into account both accuracy and efficiency, but the existing image recognition methods are all single processing methods for a single field, and they must be customized for different fields and different products. Development and deployment , poor adaptability, low efficiency

Images