An Iris Recognition System Using CNN &amp; VGG16 Technique

Singh, Arun; Pandey, Akansha; Rakhra, Manik; Singh, Dalwinder; Singh, Gurasis; Dahiya, Omdev

doi:10.1109/icrito56286.2022.9965172

Cited by 32 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The capability of the recognition system of Iris, is evaluated using the CASIA-IrisV2 iris dataset [21]. For testing, 60 classes were selected, ten images per session, and a total number of six hundred, 640x480 Bit Maps.…”

Section: Resultsmentioning

confidence: 99%

“…By conveying a high entrenching charge to the zone with significant features of Iris, a unique distortion function is suggested to reduce the effect of embedded information on iris recognition. The capability of the eye-Iris Identification system is evaluated using the CASIA -IrisV2 dataset of iris features [21]. For testing, 60 classes were selected, ten images per class & a total number of six hundred, 640x480 Bit Map pictures.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Contemporary Approaches On Reversible Data Hiding In Iris Image Using Deep Learning Techniques

2024

Proceedings of the 1st International Conference on Artificial Intelligence, Communication, IoT, Data Engineering and Security,

View full text Add to dashboard Cite

The concept of reversible data concealing is crucial for secret communication. After the extraction stages, the protected information can be completely rebuilt in addition to the hidden data being removed. Pixel, Block and Interpolation based algorithms have seen substantial development over the past decade, employing the spatial-frequency domain and other related techniques. The goal of this research work is to categorize and describe the various methods, inner groups and research papers related to the idea of Reversible Data Hiding (RDH). In order to protect privacy, this research suggests a revolutionary iris image data concealing strategy. Here, private information is incorporated into the iris image in a way that has the least negative effect on iris recognition. The Syndrome Trellis Coding (STC) architecture is applied, limiting changes to the embedded data and to the regions that infrequently affect iris identification. A new distortion function is also proposed to enumerate the impression of data implanting on recognition of Iris, which assigns high embedding cost to locations with strong iris features. According to experimental findings, enough information can be incorporated into the iris image while sustaining excellent identification accuracy by employing the proposed technique.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Contemporary Approaches On Reversible Data Hiding In Iris Image Using Deep Learning Techniques

2024

Proceedings of the 1st International Conference on Artificial Intelligence, Communication, IoT, Data Engineering and Security,

View full text Add to dashboard Cite

show abstract

“…The performance of the SkinLesNet model was compared to the ResNet50 and VGG16 models. ResNet50 [ 60 ] and VGG16 [ 61 ] were selected as benchmarks because they are popular CNN architectures known for their effectiveness in image-classification tasks, including medical-imaging applications [ 62 , 63 , 64 , 65 ]. ResNet50, part of the ResNet family, utilizes skip connections that aid in mitigating the vanishing gradient problem during training, enabling the network to effectively learn from a broader set of features [ 62 ].…”

Section: Methodsmentioning

confidence: 99%

SkinLesNet: Classification of Skin Lesions and Detection of Melanoma Cancer Using a Novel Multi-Layer Deep Convolutional Neural Network

Azeem,

Kiani,

Mansouri

et al. 2023

Cancers

View full text Add to dashboard Cite

Skin cancer is a widespread disease that typically develops on the skin due to frequent exposure to sunlight. Although cancer can appear on any part of the human body, skin cancer accounts for a significant proportion of all new cancer diagnoses worldwide. There are substantial obstacles to the precise diagnosis and classification of skin lesions because of morphological variety and indistinguishable characteristics across skin malignancies. Recently, deep learning models have been used in the field of image-based skin-lesion diagnosis and have demonstrated diagnostic efficiency on par with that of dermatologists. To increase classification efficiency and accuracy for skin lesions, a cutting-edge multi-layer deep convolutional neural network termed SkinLesNet was built in this study. The dataset used in this study was extracted from the PAD-UFES-20 dataset and was augmented. The PAD-UFES-20-Modified dataset includes three common forms of skin lesions: seborrheic keratosis, nevus, and melanoma. To comprehensively assess SkinLesNet’s performance, its evaluation was expanded beyond the PAD-UFES-20-Modified dataset. Two additional datasets, HAM10000 and ISIC2017, were included, and SkinLesNet was compared to the widely used ResNet50 and VGG16 models. This broader evaluation confirmed SkinLesNet’s effectiveness, as it consistently outperformed both benchmarks across all datasets.

show abstract

“…Table 1 compares the conventional workflow components to our approach to emphasize our contributions. Yang [5] No DualSANet Yes 3 Singh [6] No VGG16+CNN Yes 1 Alwawi [7] No CNN Yes 1 Garg [8] No BPNN Yes 1 Sun [9] No OCFON+CNN Yes…”

Section: Model Validationmentioning

confidence: 99%

“…As shown above, we demonstrated the comparison of conventional workflow components [7] [5] [8] [6] [9] to our approach. Related to the aforementioned problem, the most relevant works in the literature are discussed.…”

Section: Related Workmentioning

confidence: 99%

On Designing a SwinIris Transformer Based Iris Recognition System

Gao,

Bourlai

2024

IEEE Access

View full text Add to dashboard Cite

In this paper, we discuss our proposed unified approach to iris recognition called the SwinIris. This approach works efficiently when combing a tuned version of the original Swin Transformer with a set of iris recognition processes. While the original Swin Transformer has recently been used on different biometric modalities due to its competitive advantage over other architectures, it has not been used for iris recognition. Thus, in our work, our proposed deep learning architecture is using a pre-trained Swin Transformer model that is fine-tuned with a set of linear layers. This model is a set of algorithmic aspects that achieve competitive iris-matching accuracy when using any of the selected iris databases selected to test our approach. Specifically, our proposed SwinIris Transformer-based iris recognition system is composed of four modules, namely, the eye detection, iris detection, iris segmentation, and iris classification modules. The proposed system commences with a detection process that aims to identify eyes within the cameracaptured original iris images. Subsequently, the iris detection process identifies the iris patterns within the detected iris images to ensure that they are present and can be segmented. The third module involves iris segmentation, which extracts iris features utilized by the fourth and final module that matches iris images using the SwinIris-based Transformer model. The performance of the proposed system is evaluated on small-and large-scale iris datasets, including the CASIA-Iris-Thousand, CASIA-Iris-Lamp, CASIA-IntervalV4, and CASIA-IntervalV3. Our proposed model has a competitive iris classification accuracy when compared to various academic state-of-the-art methodologies, resulting in a classification performance ranging from 95.14% to 99.56%.

show abstract

An Iris Recognition System Using CNN & VGG16 Technique

Cited by 32 publications

References 18 publications

Contemporary Approaches On Reversible Data Hiding In Iris Image Using Deep Learning Techniques

Contemporary Approaches On Reversible Data Hiding In Iris Image Using Deep Learning Techniques

SkinLesNet: Classification of Skin Lesions and Detection of Melanoma Cancer Using a Novel Multi-Layer Deep Convolutional Neural Network

On Designing a SwinIris Transformer Based Iris Recognition System

Contact Info

Product

Resources

About