D-Talk: Sign Language Recognition System for People with Disability using Machine Learning and Image Processing

Abstract

Communication plays a significant role in making the world a better place. Communication creates bonding and relations among the people, whether persona, social, or political views. Most people communicate efficiently without any issues, but many cannot due to disability. They cannot hear or speak, which makes Earth a problematic place to live for them. Even simple basic tasks become difficult for them. Disability is an emotive human condition. It limits the individual to a certain level of performance. Being deaf and dumb pushes the subject to oblivion, highly introverted. In a world of inequality, this society needs empowerment. Harnessing technology to improve their welfare is necessary. In a tech era, no one should be limited due to his or her inability. The application of technology should create a platform or a world of equality despite the natural state of humans. On the other hand, technology is the most innovative thing on Earth for every time the clock ticks, researchers, software engineers, programmers, and information technology specialists are always coming up with bright ideas to provide convenience to everyone. This paper shows how artificial intelligence is being used to help people who are unable to do what most people do in their everyday lives. Aligned with communication, D-talk is a system that allows people who are unable to talk and hear be fully understood and for them to learn their language easier and also for the people that would interact and communicate with them. This system provides detailed hand gestures that show the interpretation at the bottom so that everyone can understand them. This research allows the readers to learn the system and what it can do to people who are struggling with what they are not capable of and will provide the technical terms on how the system works.

Research on Basketball Goal Recognition Based on Image Processing and Improved Algorithm

“…where σ 0 is an important parameter. When the value of σ 0 is selected, the weight difference of each particle should be kept in an appropriate range, and the effectiveness and diversity of particles during resampling should be ensured [12][13][14].…”

Research and application of key technologies for intelligent audit of market-based electricity sales charges based on artificial intelligence

“…(a) Iterative update of audit rule base Use big data analysis technology and machine self-learning algorithms to build a dynamic adjustment model of accounting rule thresholds, and an automatic update model of the audit rule library (new and eliminated) [6] . Use language processing basic technology to interpret policy documents [7] . Extract key content.…”

Mood Detection using Facial Recognition Technology Application in Higher Education Institution

“…It is found in the mentioned researches that committee neural networks outperform a single neural network in detecting and classification each part of the input tested images. Based on these studies, an intelligence system is developed in [8,26] to classify the human's facial expressions by using committee neural network. The developed system was able to classify the input images into seven facial expressions ("No Emotion", "happy", "sad", "disgust", "angry", "fear" and "surprised").…”