Cloth pattern recognition with four features (RSSM)

Rao, N Durga; Sudhavani, G.; Balakrishna, Prathiksha; Gouthami, K.

doi:10.1109/isacc.2015.7377315

Cited by 3 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors reported an average accuracy of 80% and recommended more training images to counter ambient light effects. Radon transform [12] appears to be a common method for discriminating colour texture patterns on clothes [13,14]. Yang et al [13] developed a clothing pattern recognition method for assisting visually impaired people using a novel feature extraction method called Radon Signature to capture the global directionality of colour patterns.…”

Section: Use Of Radon Transformmentioning

confidence: 99%

“…To capture the global patterns of clothes, Durga Rao et al [14] combined a novel Radon Transform Descriptor (RTD), Scale Invariant Feature Transform (SIFT), Mathematical Morphology (MM) based global features, and a schema for extracting Statistical Descriptor A support vector machine (SVM) classifier was trained to recognise texture patterns. The approach achieved a 96% recognition accuracy on the CCNY Clothing Pattern dataset used in [13].…”

Section: Use Of Radon Transformmentioning

confidence: 99%

“…Most of the work in literature [12][13][14] analyse the structural patterns of textures on clothes. Such approaches require enough foreground pixels and clear images free of motion blur, lens distortion, and image degradation.…”

Section: Literature Summarymentioning

confidence: 99%

See 2 more Smart Citations

Automated uniform recognition to enhance video surveillance at correctional services in South Africa

Kunene,

Zandamela,

Mabuza-Hocquet

et al. 2023

MATEC Web Conf.

View full text Add to dashboard Cite

Injuries from inmate altercations are common in correctional service facilities. Monitoring incidents manually from video surveillance can be challenging. Computer vision has the potential to assist security personnel in securing facilities. This work compares two methods for recognising occupational uniforms with the aim of improving situational awareness and safety in prisons. The first method uses histograms of hue and saturation (HS) colour-space features and a shallow learning classifier. The second method uses convolutional neural network (CNN) models trained with either hand-engineered or automatically learned features. A training dataset with civilians, South African correctional service and police uniforms was created. The experimental results demonstrate comparable performance from shallow learning algorithms and CNN models. Machine learning algorithms evaluated on the proposed colour features achieved an average balanced performance (F1-score) of 0.85 and inference times range from 0.01 to 4.9 milliseconds.

show abstract