A Novel approach for Hand Gesture Recognition using Kirsch edge with Bit Plane
| Autor: | Anupama Sharma, S. N. Tazi |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Lossless compression
Computer science business.industry Feature vector ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Binary number 02 engineering and technology 01 natural sciences Scale space Kernel (image processing) Gesture recognition 0103 physical sciences 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence Invariant (mathematics) 010306 general physics business Bit plane |
| Zdroj: | 2019 International Conference on Intelligent Computing and Control Systems (ICCS). |
| DOI: | 10.1109/iccs45141.2019.9065731 |
| Popis: | Over the last few decades, a number of researchers have proposed a variety of hand gesture recognition techniques. The paper presents a new approach for hand recognition. The preprocessing is done by applying Gaussian scale space and to enhance the feature average gray intensity has been found. The kirsch’s convolution mask is computed for edge map and has collaborated with result obtained by combining different Bit Planes. The aim of the proposed descriptor is to illuminate the noise and unwanted data and make it invariant to scale rotation and illumination changes. The local edge computation gives the result which is invariant to scale rotation but it does not tend to eliminate noise. Bit plane encoding used the binary form of image and reduce the data used to describe a series of sample values. The bit plane slicing is done through lossless binary compression technique and the bits are recombined to build the feature vector. The aim is to make the hand recognition result under rotation, illumination and roughness effective. In this paper, we summarized the proposed descriptor and compares it with other methods found in literature for recognition of the same data. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|