An integrated mediapipe-optimized GRU model for Indian sign language recognition

Abstract

Sign language recognition is challenged by problems, such as accurate tracking of hand gestures, occlusion of hands, and high computational cost. Recently, it has benefited from advancements in deep learning techniques. However, these larger complex approaches cannot manage long-term sequential data and they are characterized by poor information processing and learning efficiency in capturing useful information. To overcome these challenges, we propose an integrated MediaPipe-optimized gated recurrent unit (MOPGRU) model for Indian sign language recognition. Specifically, we improved the update gate of the standard GRU cell by multiplying it by the reset gate to discard the redundant information from the past in one screening. By obtaining feedback from the resultant of the reset gate, additional attention is shown to the present input. Additionally, we replace the hyperbolic tangent activation in standard GRUs with exponential linear unit activation and SoftMax with Softsign activation in the output layer of the GRU cell. Thus, our proposed MOPGRU model achieved better prediction accuracy, high learning efficiency, information processing capability, and faster convergence than other sequential models.

Artificial intelligence analysis of over a million Chinese men and women reveals level of dark circle in the facial skin aging process

“…Through this AI‐based automatic grading system, facial indications including Dark Circles, skin type, Pores, Acne vulgaris, and Blackheads could be analyzed automatically. The first phase is face detection using a google face detection method given an input image 13 . Geometrically normalizing the face begins with the detection of facial landmarks.…”

“…The first phase is face detection using a google face detection method given an input image. 13 Geometrically normalizing the face begins with the Then, our team employ transfer learning and ResNet50V2 as foundation model, followed by a softmax layer to provide the dark circle score, in order to achieve higher accuracy with little data. With tens of thousands of annotated images used to train the model, the accuracy of this fine-tuned model in the validation dataset is 91.5%.…”

Marathi Sign Language Recognition using MediaPipe and Deep Learning Algorithm

“…The GRU or LSTM can achieve a high recognition rate for real-time sign language recognition applications. [10], proposed and implemented the MediaPipe optimized gated recurrent unit (MOPGRU) model for Indian Sign Language (ISL) recognition. The authors update the gate of the standard GRU and also replace the hyperbolic tangent activation in standard GRUs with exponential linear unit activation and SoftMax with Softsign activation in the output layer of the GRU cell.…”

A review on computational methods based automated sign language recognition system for hearing and speech impaired community

“…The model succeeded in identifying similar hand gestures. Further to address hold time of long time sequential data, a Gated Recurrent unit integrated with mediapipe is proposed by Abbas et al 157 This method enhanced the sign prediction since the optimized GRU eliminated the irrelevant past information with the help of reset gate in primary screening. Another approach to resolve the signer independent issue was proposed by Subramanian et al 158 In his approach, he suggested a multi‐modality framework that combines CNN for feature extraction from the given input RGB videos and employs ResNet‐18 for extracting the skeleton features.…”