SegDenseNet: Iris Segmentation for Pre-and-Post Cataract Surgery

Lakra, Aditya; Tripathi, Pavani; Keshari, Rohit; Vatsa, Mayank; Singh, Richa

doi:10.1109/icpr.2018.8545840

Cited by 18 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is still room for improvements in sclera segmentation, so we intend to: 1) design new and better network architectures; 2) create a unique architecture that integrates the detection stage of the periocular region; 3) employ a post-processing stage to refine the segmentation given by the proposed approaches; 4) design a general and independent sensor approach, where firstly the image sensor is classified and then the sclera is segmented with a specific approach; 5) compare the proposed approaches with methods applied in other domains such as iris segmentation [17,19] and periocular-based recognition [26].…”

Section: Discussionmentioning

confidence: 99%

Fully Convolutional Networks and Generative Adversarial Networks Applied to Sclera Segmentation

Lucio

Laroca

Severo

et al. 2018

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

View full text Add to dashboard Cite

Due to the world's demand for security systems, biometrics can be seen as an important topic of research in computer vision. One of the biometric forms that has been gaining attention is the recognition based on sclera. The initial and paramount step for performing this type of recognition is the segmentation of the region of interest, i.e. the sclera. In this context, two approaches for such task based on the Fully Convolutional Network (FCN) and on Generative Adversarial Network (GAN) are introduced in this work. FCN is similar to a common convolution neural network, however the fully connected layers (i.e., the classification layers) are removed from the end of the network and the output is generated by combining the output of pooling layers from different convolutional ones. The GAN is based on the game theory, where we have two networks competing with each other to generate the best segmentation. In order to perform fair comparison with baselines and quantitative and objective evaluations of the proposed approaches, we provide to the scientific community new 1,300 manually segmented images from two databases 1 . The experiments are performed on the UBIRIS.v2 and MICHE databases and the best performing configurations of our propositions achieved F -score s measures of 87.48% and 88.32%, respectively.

show abstract

Section: Discussionmentioning

confidence: 99%

Fully Convolutional Networks and Generative Adversarial Networks Applied to Sclera Segmentation

Lucio

Laroca

Severo

et al. 2018

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

View full text Add to dashboard Cite

show abstract

“…Recently, researchers have proposed several techniques which outperform the performance of conventional MFT. This includes progressive network [47], block-module network [48], utilizing intermediate information of the CNN blocks [49], class-based penalty at each convolutional layer [50], and collaborative learning [51]. Keshari et al [52] have observed that the structure of the CNN filters can be learned separately.…”

Section: A Adapting Pre-trained Modelsmentioning

confidence: 99%

Unravelling Small Sample Size Problems in the Deep Learning World

Keshari¹,

Ghosh²,

Chhabra³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

The growth and success of deep learning approaches can be attributed to two major factors: availability of hardware resources and availability of large number of training samples. For problems with large training databases, deep learning models have achieved superlative performances. However, there are a lot of small sample size or S 3 problems for which it is not feasible to collect large training databases. It has been observed that deep learning models do not generalize well on S 3 problems and specialized solutions are required. In this paper, we first present a review of deep learning algorithms for small sample size problems in which the algorithms are segregated according to the space in which they operate, i.e. input space, model space, and feature space. Secondly, we present Dynamic Attention Pooling approach which focuses on extracting global information from the most discriminative sub-part of the feature map. The performance of the proposed dynamic attention pooling is analyzed with state-of-the-art ResNet model on relatively small publicly available datasets such as SVHN, C10, C100, and TinyImageNet.

show abstract

“…Most of the existing deep-learning-based iris segmentation methods [ 17 , 18 , 19 , 20 , 21 ] do not solve the above problems well, and the ideal segmentation performance of [ 18 , 19 , 20 ] is heavily dependent on large-scale data. These data must be iris pixels accurately labeled by hand, which is time-consuming and expensive.…”

Section: Introductionmentioning

confidence: 99%

Supervised Contrastive Learning and Intra-Dataset Adversarial Adaptation for Iris Segmentation

Zhou

Liu

Zhu

et al. 2022

Entropy

View full text Add to dashboard Cite

Precise iris segmentation is a very important part of accurate iris recognition. Traditional iris segmentation methods require complex prior knowledge and pre- and post-processing and have limited accuracy under non-ideal conditions. Deep learning approaches outperform traditional methods. However, the limitation of a small number of labeled datasets degrades their performance drastically because of the difficulty in collecting and labeling irises. Furthermore, previous approaches ignore the large distribution gap within the non-ideal iris dataset due to illumination, motion blur, squinting eyes, etc. To address these issues, we propose a three-stage training strategy. Firstly, supervised contrastive pretraining is proposed to increase intra-class compactness and inter-class separability to obtain a good pixel classifier under a limited amount of data. Secondly, the entire network is fine-tuned using cross-entropy loss. Thirdly, an intra-dataset adversarial adaptation is proposed, which reduces the intra-dataset gap in the non-ideal situation by aligning the distribution of the hard and easy samples at the pixel class level. Our experiments show that our method improved the segmentation performance and achieved the following encouraging results: 0.44%, 1.03%, 0.66 %, 0.41%, and 0.37% in the Nice1 and 96.66%, 98.72%, 93.21%, 94.28%, and 97.41% in the F1 for UBIRIS.V2, IITD, MICHE-I, CASIA-D, and CASIA-T.

show abstract

SegDenseNet: Iris Segmentation for Pre-and-Post Cataract Surgery

Cited by 18 publications

References 18 publications

Fully Convolutional Networks and Generative Adversarial Networks Applied to Sclera Segmentation

Fully Convolutional Networks and Generative Adversarial Networks Applied to Sclera Segmentation

Unravelling Small Sample Size Problems in the Deep Learning World

Supervised Contrastive Learning and Intra-Dataset Adversarial Adaptation for Iris Segmentation

Contact Info

Product

Resources

About