Disguise detection and face recognition in visible and thermal spectrums

Dhamecha, Tejas I.; Nigam, Aastha; Singh, Richa; Vatsa, Mayank

doi:10.1109/icb.2013.6613019

Cited by 89 publications

(39 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the surveillance system can work only in the daytime because it uses only visible light images. As proved by some previous researches [34,35,36,37], the combination of visible light and thermal images can be used to enhance the performance of several image-based systems such as pedestrian detection, disguise detection and face recognition. As claimed by these researches, the thermal images can be used as an alternative to visible images and offer some advantages such as the robustness to the change of illumination and dark environments.…”

Section: Introductionmentioning

confidence: 99%

Person Recognition System Based on a Combination of Body Images from Visible Light and Thermal Cameras

Nguyen

Hong

Kim

et al. 2017

Sensors

489

159

View full text Add to dashboard Cite

The human body contains identity information that can be used for the person recognition (verification/recognition) problem. In this paper, we propose a person recognition method using the information extracted from body images. Our research is novel in the following three ways compared to previous studies. First, we use the images of human body for recognizing individuals. To overcome the limitations of previous studies on body-based person recognition that use only visible light images for recognition, we use human body images captured by two different kinds of camera, including a visible light camera and a thermal camera. The use of two different kinds of body image helps us to reduce the effects of noise, background, and variation in the appearance of a human body. Second, we apply a state-of-the art method, called convolutional neural network (CNN) among various available methods, for image features extraction in order to overcome the limitations of traditional hand-designed image feature extraction methods. Finally, with the extracted image features from body images, the recognition task is performed by measuring the distance between the input and enrolled samples. The experimental results show that the proposed method is efficient for enhancing recognition accuracy compared to systems that use only visible light or thermal images of the human body.

show abstract

Section: Introductionmentioning

confidence: 99%

Person Recognition System Based on a Combination of Body Images from Visible Light and Thermal Cameras

Nguyen

Hong

Kim

et al. 2017

Sensors

489

159

View full text Add to dashboard Cite

show abstract

“…They can also be used to adapt the filters from one task to another task while learning only the strength of the filters. The proposed algorithm can also be extended to other applications such as face recognition with variations in disguise [7], matching faces in videos [14], and sketch to photo matching [33].…”

Section: Algorithmmentioning

confidence: 99%

Learning Structure and Strength of CNN Filters for Small Sample Size Training

Keshari

Vatsa

Singh

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

Self Cite

View full text Add to dashboard Cite

Convolutional Neural Networks have provided state-ofthe-art results in several computer vision problems. However, due to a large number of parameters in CNNs, they require a large number of training samples which is a limiting factor for small sample size problems. To address this limitation, we propose SSF-CNN which focuses on learning the "structure" and "strength" of filters. The structure of the filter is initialized using a dictionary based filter learning algorithm and the strength of the filter is learned using the small sample training data. The architecture provides the flexibility of training with both small and large training databases, and yields good accuracies even with small size training data. The effectiveness of the algorithm is first demonstrated on MNIST, CIFAR10, and NORB databases, with varying number of training samples. The results show that SSF-CNN significantly reduces the number of parameters required for training while providing high accuracies on the test databases. On small sample size problems such as newborn face recognition and Omniglot, it yields stateof-the-art results. Specifically, on the IIITD Newborn Face Database, the results demonstrate improvement in rank-1 identification accuracy by at least 10%.

show abstract

“…Most recently, Gupta et al [10] proposed a Scattering Transform for matching surgically altered face images. There has been limited research in the field of face recognition in the presence of disguises [7,8,19,20,24]. Recently, as part of CVPR 2018 workshop and competition, the largest publicly available Disguised Faces in the Wild (DFW) database [8] [14] was released, which contains variations due to impersonation and obfuscation.…”

Section: Variationsmentioning

confidence: 99%

On Matching Faces with Alterations due to Plastic Surgery and Disguise

Suri

Sankaran²,

Vatsa

et al. 2018

2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems (BTAS)

Self Cite

View full text Add to dashboard Cite

Plastic surgery and disguise variations are two of the most challenging co-variates of face recognition. The stateof-art deep learning models are not sufficiently successful due to the availability of limited training samples. In this paper, a novel framework is proposed which transfers fundamental visual features learnt from a generic image dataset to supplement a supervised face recognition model. The proposed algorithm combines off-the-shelf supervised classifier and a generic, task independent network which encodes information related to basic visual cues such as color, shape, and texture. Experiments are performed on IIITD plastic surgery face dataset and Disguised Faces in the Wild (DFW) dataset. Results showcase that the proposed algorithm achieves state of the art results on both the datasets. Specifically on the DFW database, the proposed algorithm yields over 87% verification accuracy at 1% false accept rate which is 53.8% better than baseline results computed using VGGFace.

show abstract

Disguise detection and face recognition in visible and thermal spectrums

Cited by 89 publications

References 22 publications

Person Recognition System Based on a Combination of Body Images from Visible Light and Thermal Cameras

Person Recognition System Based on a Combination of Body Images from Visible Light and Thermal Cameras

Learning Structure and Strength of CNN Filters for Small Sample Size Training

On Matching Faces with Alterations due to Plastic Surgery and Disguise

Contact Info

Product

Resources

About