Image and video data are today being shared between government entities and other relevant stakeholders on a regular basis and require careful handling of the personal information contained therein. A popular approach to ensure privacy protection in such data is the use of deidentification techniques, which aim at concealing the identity of individuals in the imagery while still preserving certain aspects of the data after deidentification. In this work, we propose a novel approach towards face deidentification, called k-Same-Net, which combines recent Generative Neural Networks (GNNs) with the well-known k-Anonymitymechanism and provides formal guarantees regarding privacy protection on a closed set of identities. Our GNN is able to generate synthetic surrogate face images for deidentification by seamlessly combining features of identities used to train the GNN model. Furthermore, it allows us to control the image-generation process with a small set of appearance-related parameters that can be used to alter specific aspects (e.g., facial expressions, age, gender) of the synthesized surrogate images. We demonstrate the feasibility of k-Same-Net in comprehensive experiments on the XM2VTS and CK+ datasets. We evaluate the efficacy of the proposed approach through reidentification experiments with recent recognition models and compare our results with competing deidentification techniques from the literature. We also present facial expression recognition experiments to demonstrate the utility-preservation capabilities of k-Same-Net. Our experimental results suggest that k-Same-Net is a viable option for facial deidentification that exhibits several desirable characteristics when compared to existing solutions in this area.

Object detection and segmentation represents the basis for many tasks in computer and machine vision. In biometric recognition systems the detection of the region‐of‐interest (ROI) is one of the most crucial steps in the processing pipeline, significantly impacting the performance of the entire recognition system. Existing approaches to ear detection, are commonly susceptible to the presence of severe occlusions, ear accessories or variable illumination conditions and often deteriorate in their performance if applied on ear images captured in unconstrained settings. To address these shortcomings, we present a novel ear detection technique based on convolutional encoder‐decoder networks (CEDs). We formulate the problem of ear detection as a two‐class segmentation problem and design and train a CED‐network architecture to distinguish between image‐pixels belonging to the ear and the non‐ear class. Unlike competing techniques, our approach does not simply return a bounding box around the detected ear, but provides detailed, pixel‐wise information about the location of the ears in the image. Experiments on a dataset gathered from the web (a.k.a. in the wild) show that the proposed technique ensures good detection results in the presence of various covariate factors and significantly outperforms competing methods from the literature.

In recent years, there has been increasing interest in the conversion of images into audio descriptions. This is a field that lies at the intersection of Computer Vision (CV) and Natural Language Processing (NLP), and it involves various tasks, including creating textual descriptions of images and converting them directly into auditory representations. Another aspect of this field is the synthesis of natural speech from text. This has significant potential to improve accessibility, user experience, and the applications of Artificial Intelligence (AI). In this article, we reviewed a wide range of image-to-audio conversion techniques. Various aspects of image captioning, speech synthesis, and direct image-to-speech conversion have been explored, from fundamental encoder–decoder architectures to more advanced methods such as transformers and adversarial learning. Although the focus of this review is on synthesizing audio descriptions from visual data, the reverse task of creating visual content from natural language descriptions is also covered. This study provides a comprehensive overview of the techniques and methodologies used in these fields and highlights the strengths and weaknesses of each approach. The study emphasizes the importance of various datasets, such as MS COCO, LibriTTS, and VizWiz Captions, which play a critical role in training models, evaluating them, promoting inclusivity, and solving real-world problems. The implications for the future suggest the potential of generating more natural and contextualized audio descriptions, whereas direct image-to-speech tasks provide opportunities for intuitive auditory representations of visual content.

In this chapter, we address the problem of biometric identity recognition from the vasculature of the human sclera. Specifically, we focus on the challenging task of multi-view sclera recognition, where the visible part of the sclera vasculature changes from image to image due to varying gaze (or view) directions. We propose a complete solution for this task built around Convolutional Neural Networks (CNNs) and make several contributions that result in state-of-the-art recognition performance, i.e.: (i) we develop a cascaded CNN assembly that is able to robustly segment the sclera vasculature from the input images regardless of gaze direction, and (ii) we present ScleraNET, a CNN model trained in a multi-task manner (combining losses pertaining to identity and view-direction recognition) that allows for the extraction of discriminative vasculature descriptors that can be used for identity inference. To evaluate the proposed contributions, we also introduce a new dataset of ocular images, called the Sclera Blood Vessels, Periocular and Iris (SBVPI) dataset, which represents one of the few publicly available datasets suitable for research in multi-view sclera segmentation and recognition. The datasets come with a rich set of annotations, such as a per-pixel markup of various eye parts (including the sclera vasculature), identity, gaze-direction and gender labels. We conduct rigorous experiments on SBVPI with competing techniques from the literature and show that the combination of the proposed segmentation and descriptor-computation models results in highly competitive recognition performance.