Explicit Over Implicit: Enhancing CNNs Via Complex Structure Tensor Representations for Periocular Recognition

• URL: http://arxiv.org/abs/2607.15410v1
• Date: Thu, 16 Jul 2026 19:22:22 GMT
• Title: Explicit Over Implicit: Enhancing CNNs Via Complex Structure Tensor Representations for Periocular Recognition
• Abstract summary: We show that using the Complex Structure, which contains compact orientation features with certainties, as input to CNNs consistently improves identification accuracy.<n>This suggests that the upfront use of orientation features in CNNs, a strategy seen in mammalian vision, not only mitigates their limitations but also enhances their explainability and relevance to thin-clients.
• Score: 40.158607931758084
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Our study provides evidence that CNNs struggle to extract orientation features effectively. We show that using the Complex Structure Tensor, which contains compact orientation features with certainties, as input to CNNs consistently improves identification accuracy compared to grayscale inputs alone. Experiments also demonstrated that our inputs, provided by mini-complex convnets, combined with reduced CNN sizes, outperformed full-fledged, prevailing CNN architectures. This suggests that the upfront use of orientation features in CNNs, a strategy seen in mammalian vision, not only mitigates their limitations but also enhances their explainability and relevance to thin-clients. Experiments were conducted on publicly available datasets comprising periocular images (Cross-Eyed and PolyU) for biometric identification and verification in both Close-World and Open-World Scenarios using six CNN architectures. Our experiments on the Cross-Eyed and PolyU datasets yield a 5-26% reduction in EER, providing strong empirical evidence that explicit orientation priors mitigate CNN representational limits in Open-World and Close-World scenarios.

Related papers

• Effects of Gabor Filters on Classification Performance of CNNs Trained on a Limited Number of Conditions [0.0]
  We propose a technique to improve the accuracy and reduce the size of convolutional neural networks (CNNs) running on edge devices for real-world robot vision applications.<n>We used a Gabor filter, a model of the feature extractor of the visual nervous system, as a preprocessor for CNNs to investigate the accuracy of the CNNs trained with small amounts of data.
  arXiv  Detail & Related papers  (2026-01-17T05:36:30Z)
• Impact of White-Box Adversarial Attacks on Convolutional Neural Networks [0.6138671548064356]
  We investigate the susceptibility of Convolutional Neural Networks (CNNs) to white-box adversarial attacks. Our study provides insights into the robustness of CNNs against adversarial threats.
  arXiv  Detail & Related papers  (2024-10-02T21:24:08Z)
• Understanding and Improving CNNs with Complex Structure Tensor: A Biometrics Study [47.03015281370405]
  We show that the use of Complex Structure, which contains compact orientation features with certainties, improves identification accuracy compared to using grayscale inputs alone. This suggests that the upfront use of orientation features in CNNs, a strategy seen in mammalian vision, not only mitigates their limitations but also enhances their explainability and relevance to thin-clients.
  arXiv  Detail & Related papers  (2024-04-24T02:51:13Z)
• Demystifying CNNs for Images by Matched Filters [13.121514086503591]
  convolution neural networks (CNN) have been revolutionising the way we approach and use intelligent machines in the Big Data era. CNNs have been put under scrutiny owing to their textitblack-box nature, as well as the lack of theoretical support and physical meanings of their operation. This paper attempts to demystify the operation of CNNs by employing the perspective of matched filtering.
  arXiv  Detail & Related papers  (2022-10-16T12:39:17Z)
• SAR Despeckling Using Overcomplete Convolutional Networks [53.99620005035804]
  despeckling is an important problem in remote sensing as speckle degrades SAR images. Recent studies show that convolutional neural networks(CNNs) outperform classical despeckling methods. This study employs an overcomplete CNN architecture to focus on learning low-level features by restricting the receptive field. We show that the proposed network improves despeckling performance compared to recent despeckling methods on synthetic and real SAR images.
  arXiv  Detail & Related papers  (2022-05-31T15:55:37Z)
• BreakingBED -- Breaking Binary and Efficient Deep Neural Networks by Adversarial Attacks [65.2021953284622]
  We study robustness of CNNs against white-box and black-box adversarial attacks. Results are shown for distilled CNNs, agent-based state-of-the-art pruned models, and binarized neural networks.
  arXiv  Detail & Related papers  (2021-03-14T20:43:19Z)
• The Mind's Eye: Visualizing Class-Agnostic Features of CNNs [92.39082696657874]
  We propose an approach to visually interpret CNN features given a set of images by creating corresponding images that depict the most informative features of a specific layer. Our method uses a dual-objective activation and distance loss, without requiring a generator network nor modifications to the original model.
  arXiv  Detail & Related papers  (2021-01-29T07:46:39Z)
• Teaching CNNs to mimic Human Visual Cognitive Process & regularise Texture-Shape bias [18.003188982585737]
  Recent experiments in computer vision demonstrate texture bias as the primary reason for supreme results in models employing Convolutional Neural Networks (CNNs) It is believed that the cost function forces the CNN to take a greedy approach and develop a proclivity for local information like texture to increase accuracy, thus failing to explore any global statistics. We propose CognitiveCNN, a new intuitive architecture, inspired from feature integration theory in psychology to utilise human interpretable feature like shape, texture, edges etc. to reconstruct, and classify the image.
  arXiv  Detail & Related papers  (2020-06-25T22:32:54Z)
• Hold me tight! Influence of discriminative features on deep network boundaries [63.627760598441796]
  We propose a new perspective that relates dataset features to the distance of samples to the decision boundary. This enables us to carefully tweak the position of the training samples and measure the induced changes on the boundaries of CNNs trained on large-scale vision datasets.
  arXiv  Detail & Related papers  (2020-02-15T09:29:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.