scholarly journals Human Face Detection: Manual vs. Kohonen Self Organizing Map

2020 ◽  
Author(s):  
Samir Bandyopadhyay ◽  
Payel Bose
Keyword(s):  
Face Detection ◽  
Color Image ◽  
Input Device ◽  
Self Organizing Map ◽  
Human Face ◽  
Lighting Condition ◽  
Automated Method ◽  
Structure Changes ◽  
Face Structure ◽  
Self Organizing

In today's world it is very much important to maintain the security of information and its risks. The biometric-based techniques are very much useful in these problems. Among the several kinds of biometric-based technique, face detection is much complex and much more important. Due to the age and several other problems, a human face structure changes over time, again a human has lots of expressions. Sometimes due to the lighting condition or the variation of the angle of an input device, the pattern of a human face structure also changed. As a result, the face cannot be detected properly. In this paper, a method is proposed that can detect the human faces both automatically and manually very efficiently. In manual mode, a user can select the input faces referred by the system according to their choice. In automated mode, the system detected all possible face areas using the Kohonen Self-Organizing Feature Map technique. This method reduced the complex color image into a vector quantized image with desired colors. Then a color segmentation technique is used to detect the possible face skin areas from the vector quantized image. Then the Histogram Oriented Gradient technique used to detect the feature from the faces and K-Nearest Neighbour Classifier is used to compare both face images detected by the two modes. The automated method prosed better accuracy than the manual method.

scholarly journals Enhancement Image Intensity of HSV Color Space

2019 ◽  
Vol 8 (2S11) ◽  
pp. 2583-2585
Keyword(s):  
Light Intensity ◽  
Face Detection ◽  
Color Image ◽  
Color Space ◽  
Detection Performance ◽  
Lighting Condition ◽  
Hsv Color Space ◽  
Number Of Faces ◽  
Intensity Normalization ◽  
Poor Lighting

One of factor that affects technology in face detecting or recognizing is illumination. Poor lighting can cause difficulty to the system to recognize face. Although it is over exposure or under exposure. By doing color image processing, it supports the system to detect face in a poor lighting condition. This research used lighting intensity normalization method to increase face detection performance. This method can normalize the light intensity especially on the face lighting. We normalize the light intensity through HSV color space. HSV color space has saturation which is amount of light in the image. The method proceed saturation in image to increase face detection performance. Total number of faces we had tested is 286 faces, the system detect 243 faces before intensity normalization proceed. Whereas, after normalization process, it detects more faces which is 279 faces. As we can see, the percentage improvement before to after intensity normalization is 84.97% to 97.55%. This is 12.58% improvement. We can say this method helps face detection to increase it performance.

scholarly journals An Effective Color Quantization Method Using Octree-Based Self-Organizing Maps

2016 ◽  
Vol 2016 ◽  
pp. 1-11 ◽  
Author(s):  
Hyun Jun Park ◽  
Kwang Baek Kim ◽  
Eui-Young Cha
Keyword(s):  
Image Processing ◽  
Processing Time ◽  
Color Image ◽  
Color Image Processing ◽  
Self Organizing Map ◽  
Original Image ◽  
Color Quantization ◽  
Quantization Method ◽  
Self Organizing Maps ◽  
Self Organizing

Color quantization is an essential technique in color image processing, which has been continuously researched. It is often used, in particular, as preprocessing for many applications. Self-Organizing Map (SOM) color quantization is one of the most effective methods. However, it is inefficient for obtaining accurate results when it performs quantization with too few colors. In this paper, we present a more effective color quantization algorithm that reduces the number of colors to a small number by using octree quantization. This generates more natural results with less difference from the original image. The proposed method is evaluated by comparing it with well-known quantization methods. The experimental results show that the proposed method is more effective than other methods when using a small number of colors to quantize the colors. Also, it takes only 71.73% of the processing time of the conventional SOM method.

Sign in / Sign up

Export Citation Format

Share Document