Unlock instant, AI-driven research and patent intelligence for your innovation.

An Image Classification Method Based on Brightness and Contrast

A classification method and contrast technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of high power consumption, low contrast, unable to meet the requirements of 16.7 milliseconds of video playback, to improve applicability, guarantee show effect

Active Publication Date: 2015-09-09
HEFEI UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Liquid crystal display has two inherent defects: low contrast and high power consumption
If the image classification method is too complicated, it cannot be guaranteed that all actions of dynamic dimming can be completed within 16.7 milliseconds, so it cannot be used for dynamic dimming
Taking the invention patent "A Method for Classifying Remote Sensing Images" (authorized announcement number: CN 101067659 B) as an example, even if the same hardware implementation method (FPGA) as the present invention is used, the fastest classification calculation process for an image still needs about 70 milliseconds, which cannot meet the requirement of 16.7 milliseconds for video playback

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An Image Classification Method Based on Brightness and Contrast
  • An Image Classification Method Based on Brightness and Contrast
  • An Image Classification Method Based on Brightness and Contrast

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] Embodiment 1 divides images into 6 categories, namely, high brightness and high contrast, medium brightness and high contrast, low brightness and high contrast, high brightness and low contrast, medium brightness and low contrast, and low brightness and low contrast. see image 3 ,in image 3 a is one of the 100 images with different contents played when determining the classification threshold, image 3 b is the image to be classified, image 3 c is the classification flow chart. The image resolution is 1024×768. The specific classification steps are as follows:

[0036] 1. Determine the number of image categories according to design requirements and hardware resources: Embodiment 1 divides images into 6 categories, namely high brightness and high contrast, medium brightness and high contrast, low brightness and high contrast, high brightness and low contrast, medium brightness and low contrast, low low brightness contrast;

[0037] 2. Organize 6 natural persons ...

Embodiment 2

[0061] Embodiment 2 divides images into 9 categories, namely high brightness and high contrast, medium brightness and high contrast, low brightness and high contrast, high brightness and medium contrast, medium brightness and medium contrast, low brightness and medium contrast, high brightness and low contrast, medium brightness and low contrast , Low brightness and low contrast. see Figure 4 ,in Figure 4 a is one of the 100 images with different contents played when determining the classification threshold, Figure 4 b is the image to be classified, Figure 4 c is the classification flow chart. The image resolution is 1920×1080. The specific classification steps are as follows:

[0062] 1. Determine the number of image categories according to design requirements and hardware resources: Embodiment 2 divides images into 9 categories, namely high brightness and high contrast, medium brightness and high contrast, low brightness and high contrast, high brightness and medium...

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

No PUM Login to View More

Abstract

The invention relates to an image classification method based on brightness and contrast ratio. The image classification method based on the brightness and the contrast ratio comprises the following steps: the first step is determining the category number according to design requirements and hardware resources; the second step is organizing more than two persons with normal eyesight to watch more than forty images with different content and putting the images into different categories according to subjective feelings of the persons; the third step is calculating the brightness and the contrast ratio when the images are watched; the fourth step is determining brightness classification threshold values and brightness classification threshold values of the images in different categories according to the survey results of the second step and the calculating results of the third step; the fifth step is calculating a brightness average value Lavg and contrast ratio CR for image inputting of a video source; and the sixth step is carrying out image classification according to classification threshold values, the brightness average Lavg and the contrast ratio CR. According to the image classification method based on the brightness and the contrast ratio, the first step, the second step, the third step and the fourth step can be accomplished firstly, after the classification threshold values are obtained, the classification threshold values can be directly written into a circuit development procedure, real-time processing time is saved, dynamic light adjusting and processing time based on image classification is not longer than three milliseconds by adopting the method, and the requirement of video playing for 16.7 milliseconds is completely met.

Description

technical field [0001] The invention belongs to the technical field of liquid crystal display, and in particular relates to backlight dynamic dimming technology. Background technique [0002] Liquid crystal displays have two inherent flaws: low contrast and high power consumption. The backlight dynamic dimming technology can dynamically reduce the brightness of the backlight according to the displayed image, thereby reducing energy consumption and improving contrast. However, the currently existing dynamic dimming methods (except the maximum value method) all have certain applicability, that is, for some images, the energy saving and display effect are better, while for other images, either the energy saving effect is limited, or there is a large display distortion. As a result, the dynamic dimming technology cannot be widely used in practice. For example, the currently popular Inverse of Mapping Function (IMF) has a better energy-saving effect on images with higher overal...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G09G3/34
Inventor 冯奇斌何会杰吕国强
Owner HEFEI UNIV OF TECH