Efficient Scale Invariant and Back Propagation Neural Network Method using LIP Region Segmentation
Shaifali Sharma1, Geetanjali Babbar2, Ishdeep Singla3, Gagandeep Jindal4

1Shaifali Sharma, Department of CEC, Chandigarh Group of Colleges, Landran (Mohali), India.

2Geetanjali Babbar, Department of CEC, Chandigarh Group of Colleges, Landran (Mohali), India.

3Ishdeep Singlaa, Department of CEC, Chandigarh Group of Colleges, Landran (Mohali), India.

4Gagandeep Jindal, Department of CEC, Chandigarh Group of Colleges, Landran (Mohali), India.

Manuscript received on 08 August 2019 | Revised Manuscript received on 14 August 2019 | Manuscript Published on 26 August 2019 | PP: 873-877 | Volume-8 Issue-9S August 2019 | Retrieval Number: I11140789S19/19©BEIESP | DOI: 10.35940/ijitee.I1140.0789S19

Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: With the advent of technological sensor devices and human interface machine technology, there has been extensive research done in lip segmentation methods by several researchers — some linguistic features required for interaction with the machine equipment. Therefore, research work has been done in the audio speech detection scheme for recognition of lip reading. Visual lip reading technology developed based on the extraction of features of the lip. Lip segmentation is an essential approach to recognize lip reading scheme. Meanwhile, it helps to improve parameters. Several methods studied to segment the lip area based on localized active contour method using twice contour finding and combined color-space method. Apply the illumination histogram equalization to real color images to reduce the distortion of uneven illumination. The proposed method implemented can get better accuracy rate and segmentation results and compare with the existing process using area or circle as the region to segment grayscale images and combined in the color-space image. Using SIFT and BPNN, the inner region of the lip found in the result. The experiment tool is used MATLAB 2016a and designs a PROJECT APPLICATION. Improve the success rate and reduce the segmented error and compared with the current metrics. The experimental analysis determines the accuracy rate with 94%; error rate reduces with Segmented Error % and Overlap Error rate value with 79.73%.

Keywords: Lip Segmentation, Feature Extraction – Scale Invariant Feature Transformation, BPNN – Back Propagation Neural Network, and Active Contour.
Scope of the Article: Network Management, Reliability and QoS