Spelled sign word recognition using key frame

Rokade, Rajeshree S.; Doye, Dharmpal D.

doi:10.1049/iet-ipr.2012.0691

Cited by 11 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Human motion is characterized by certain continuity, leading to a large number of redundant frames in motion video [33]. In order to quickly obtain valid information, the motion abrupt frame will be used as a key frame for extracting key information from the human video [34], [35].…”

Section: Human Motion Target Recognition Algorithm Based On Cnn and Global Constraint Block Matching A Extraction Of Key Frames From The mentioning

confidence: 99%

Human Motion Target Recognition Using Convolutional Neural Network and Global Constraint Block Matching

Liu

2020

IEEE Access

View full text Add to dashboard Cite

The traditional human behavior recognition algorithm is easy to ignore the spatial constraint problem of feature blocks, which leads to poor recognition effect and low correct rate. Therefore, we proposed a human motion target recognition algorithm based on Convolution Neural Network (referred to as the ''CNN'') and global constraint block matching. First, key frames of the human motion video were extracted, second, the local feature and global feature of key frames were analyzed, and CNN was used to perform feature fusion, then, according to the result of the feature fusion, a feature block was formed and the closest matching feature block is obtained, using the definition of spatial constraint, we considered the spatial data of human motion in the vertical direction, calculates the spatial constraint weight, and further completes the matching. Finally, the score of matching block and the spatial constraint weight were calculated, and the human motion targets are recognized based on the cumulative score. The experimental results show that the proposed algorithm has a high key frame extraction accuracy of more than 90% and less time consumed in feature fusion, high matching accuracy of feature blocks of more than 80%, and high feature blocks, the F-measure of human behavior recognition is 0.95 on average, and the overall recognition performance is good.INDEX TERMS Convolutional neural network, global constraint block, feature block, spatial constraints, matching, human motion target, recognition.

show abstract

Section: Human Motion Target Recognition Algorithm Based On Cnn and Global Constraint Block Matching A Extraction Of Key Frames From The mentioning

confidence: 99%

Human Motion Target Recognition Using Convolutional Neural Network and Global Constraint Block Matching

Liu

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The actual output of each output node is then compared with the trained or the desired output. If there is no difference the training of the network stops else the iterative process of changing the weights of the nodes are performed until the difference between the actual and the trained outputs is minimized (Liang et al, 2015;Rokade et al, 2014).…”

Section: Feed -Forward Networkmentioning

confidence: 99%

Analysis on Hand Gesture Recognition Using Artificial Neural Network

Chauhan¹,

Maurya²,

Tiwary³

et al. 2020

Ethics and Information Technology

View full text Add to dashboard Cite

“…In [24], Rajeshree et.al offered a new method for sign language word recognition with 2-fold. By giving input as a video, the system can recognize any spelled word or alphabetic sequence signed in American Sign Language.…”

Section: Literature Reviewmentioning

confidence: 99%

An Enhanced Framework for Sign Gesture Recognition using Hidden Markov Model and Adaptive Histogram Technique

Kaluri¹,

Reddy²

2017

IJIES

View full text Add to dashboard Cite

Gesture based communication is the fundamental method for correspondence for those with hearing and vocal incapacities. Communication via gestures comprises of making shapes or developments with human hands as for the head or other body parts. In this paper, we propose a new framework for recognizing sign gestures by using Hidden Markov Model (HMM) and Histogram based methods. Initially, the noise of an image will be eliminated by Wiener Filter and the image will be segmented with the help of Histogram oriented methods -Adaptive Histogram technique and then features will be extracted. The extracted features will be given to the HMM for training and recognition of gestures. Our experimental results show a better performance in terms of recognizing gestures from a blurred image compared to the existing segmentation methods.

show abstract

Spelled sign word recognition using key frame

Cited by 11 publications

References 14 publications

Human Motion Target Recognition Using Convolutional Neural Network and Global Constraint Block Matching

Human Motion Target Recognition Using Convolutional Neural Network and Global Constraint Block Matching

Analysis on Hand Gesture Recognition Using Artificial Neural Network

An Enhanced Framework for Sign Gesture Recognition using Hidden Markov Model and Adaptive Histogram Technique

Contact Info

Product

Resources

About