Indonesian Sign Language Number Recognition using SIFT Algorithm

[摘要] Indonesian sign language (ISL) is generally used for deaf individuals and poor people communication in communicating. They use sign language as their primary language which consists of 2 types of action: sign and finger spelling. However, not all people understand their sign language so that this becomes a problem for them to communicate with normal people. this problem also becomes a factor they are isolated feel from the social life. It needs a solution that can help them to be able to interacting with normal people. Many research that offers a variety of methods in solving the problem of sign language recognition based on image processing. SIFT (Scale Invariant Feature Transform) algorithm is one of the methods that can be used to identify an object. SIFT is claimed very resistant to scaling, rotation, illumination and noise. Using SIFT algorithm for Indonesian sign language recognition number result rate recognition to 82% with the use of a total of 100 samples image dataset consisting 50 sample for training data and 50 sample images for testing data. Change threshold value get affect the result of the recognition. The best value threshold is 0.45 with rate recognition of 94%.

[发布机构] Electrical Engineering Department, State Polytechnic of Malang, Malang, Indonesia^1

[效力级别] 教育 [学科分类] 发展心理学和教育心理学

[关键词] Finger spelling;Image datasets;Number recognition;Scale invariant feature transforms;SIFT algorithms;Sign Language recognition;Threshold-value;Training data