Image classifier generating method and device as well as image classifying method and device

Abstract

The invention provides an image classifier generating method and device as well as an image classifying method and device. The method for generating an image classifier for form sorting equipment comprises the following steps: extracting a plurality of local features from each sample image in a plurality of sample images; dividing the sample image into a plurality of sub-areas; grouping local features which are extracted from the sample images and at least associated with the same sub-area into a same group; generating a search tree corresponding to the same sub-area according to the local features in the same group to serve as the image classifier.

Description

technical field [0001] The present application generally relates to the field of image processing, and more specifically, relates to a method and device for generating an image classifier and an image classification method and device. Background technique [0002] Image classification is an important aspect in the field of image processing. In the field of image processing, many image processing needs to be carried out according to the results of image classification. Therefore, the validity and accuracy of image classification play a vital role in many image processing in the field of image processing. [0003] A document image is one image type among various image types. Document images generally have a fixed layout format, and specific examples thereof include form images, license images, certificate images, receipt images, invoice images, and the like. Document images generally include pre-printed content and post-printed content, wherein the pre-printed content usual...

AI Technical Summary

Problems solved by technology

The disadvantage of this technology is that it is difficult to avoid the tedious process of formulating templates, writing rules and confirming the system

Also, some techniques use the result of character recognition, but if the image quality deteriorates, the recognition result becomes unreliable, resulting in poor classification results

In addition, there is also a technology for classifying images based on machine learning in the prior art, but this technology requires a large number of manually labeled samples as a training set

However, in practical applications, due to reasons such as copyright protection and information security, it is usually not easy to obtain real training samples, which makes the technology of image classification based on machine learning difficult to apply in practice.

In addition, in the prior art, there is also a technology for image classification based on graphic matching. Although this technology does not require a large amount of training data, its scope of application is often limited to a specific format (such as the Manhattan plate, etc.), or is Assuming perfect image segmentation can be obtained

Therefore, the technology of image classification based on pattern matching is also difficult to apply in practice.

Images