Colour segmentation for multiple low dynamic range images using boosted cascaded classifiers

Barczak, Andre L. C.; Sušnjak, Teo; Reyes, Napoleon H.; Johnson, Martin

doi:10.1109/ivcnz.2013.6727005

Cited by 8 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This section provides an overview of the datasets used for performance evaluation: the ASL dataset [20], the ASL with Digits dataset [21], and the NUS Hand Posture dataset [22].…”

Section: Datasetsmentioning

confidence: 99%

LAVRF: Sign language recognition via Lightweight Attentive VGG16 with Random Forest

Ewe,

Lee,

Lim

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Sign language recognition presents significant challenges due to the intricate nature of hand gestures and the necessity to capture fine-grained details. In response to these challenges, a novel approach is proposed—Lightweight Attentive VGG16 with Random Forest (LAVRF) model. LAVRF introduces a refined adaptation of the VGG16 model integrated with attention modules, complemented by a Random Forest classifier. By streamlining the VGG16 architecture, the Lightweight Attentive VGG16 effectively manages complexity while incorporating attention mechanisms that dynamically concentrate on pertinent regions within input images, resulting in enhanced representation learning. Leveraging the Random Forest classifier provides notable benefits, including proficient handling of high-dimensional feature representations, reduction of variance and overfitting concerns, and resilience against noisy and incomplete data. Additionally, the model performance is further optimized through hyperparameter optimization, utilizing the Optuna in conjunction with hill climbing, which efficiently explores the hyperparameter space to discover optimal configurations. The proposed LAVRF model demonstrates outstanding accuracy on three datasets, achieving remarkable results of 99.98%, 99.90%, and 100% on the American Sign Language, American Sign Language with Digits, and NUS Hand Posture datasets, respectively.

show abstract

“…This section provides an overview of the datasets used for performance evaluation: the ASL dataset [20], the ASL with Digits dataset [21], and the NUS Hand Posture dataset [22].…”

Section: Datasetsmentioning

confidence: 99%

LAVRF: Sign language recognition via Lightweight Attentive VGG16 with Random Forest

Ewe,

Lee,

Lim

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Two-dimensional CNNs have been frequently used for digit and letter signs, which usually do not contain temporal information and consist of static images. Damaneh et al [7] proposed a hybrid method using CNN, Gabor Filter, and ORB feature descriptor for recognizing static hand gestures, achieving accuracies of 99.92%, 99.8%, and 99.80% on the Massey [27], American Sign Language (ASL) alphabet [28], and ASL datasets [29], respectively. Das et al [30] used a hybrid method combining CNN and Random Forest classifiers to accurately predict numerals and characters in Bangla Sign Language with accuracies of 97.33% and 91.67%, respectively.…”

Section: Related Workmentioning

confidence: 99%

Multi-Stream Isolated Sign Language Recognition Based on Finger Features Derived from Pose Data

Akdag,

Baykan

2024

Electronics

View full text Add to dashboard Cite

This study introduces an innovative multichannel approach that focuses on the features and configurations of fingers in isolated sign language recognition. The foundation of this approach is based on three different types of data, derived from finger pose data obtained using MediaPipe and processed in separate channels. Using these multichannel data, we trained the proposed MultiChannel-MobileNetV2 model to provide a detailed analysis of finger movements. In our study, we first subject the features extracted from all trained models to dimensionality reduction using Principal Component Analysis. Subsequently, we combine these processed features for classification using a Support Vector Machine. Furthermore, our proposed method includes processing body and facial information using MobileNetV2. Our final proposed sign language recognition method has achieved remarkable accuracy rates of 97.15%, 95.13%, 99.78%, and 95.37% on the BosphorusSign22k-general, BosphorusSign22k, LSA64, and GSL datasets, respectively. These results underscore the generalizability and adaptability of the proposed method, proving its competitive edge over existing studies in the literature.

show abstract

“…With their proposed model, they were able to achieve an accuracy of 83.29%. Masood, Thuwal, and Srivastava (2018) used VGG16 model to classify 36 different hand gestures (26 alphabets and 10 numerals) of ASL from the dataset given by Barczak, Reyes, Abastillas, Piccio, and Susnjak (2011). They initialized the parameters of their model by transferring weights from the VGG16 network pretrained on Ima-geNet dataset which consists of more than a million images of 1000 categories.…”

Section: American Sign Language (Asl)mentioning

confidence: 99%

A hybrid approach for Bangla sign language recognition using deep transfer learning model with random forest classifier

Das

Imtiaz²,

Neom³

et al. 2023

Expert Systems with Applications

View full text Add to dashboard Cite

Colour segmentation for multiple low dynamic range images using boosted cascaded classifiers

Cited by 8 publications

References 16 publications

LAVRF: Sign language recognition via Lightweight Attentive VGG16 with Random Forest

LAVRF: Sign language recognition via Lightweight Attentive VGG16 with Random Forest

Multi-Stream Isolated Sign Language Recognition Based on Finger Features Derived from Pose Data

A hybrid approach for Bangla sign language recognition using deep transfer learning model with random forest classifier

Contact Info

Product

Resources

About