This paper provides a comprehensive analysis of recent developments in face recognition, tracking, identification, and person detection technologies, highlighting the benefits and drawbacks of the available techniques. To assess the state-of-art in these domains, we reviewed more than one hundred eminent journal articles focusing on current trends and research gaps in machine learning and deep learning methods. A systematic review using the PRISMA method helped us to generalize the search for the most relevant articles in this area. Based on our screening and evaluation procedures, we found and examined 142 relevant papers, evaluating their reporting compliance, sufficiency, and methodological quality. Our findings highlight essential methods of person detection, tracking and identification, and face recognition tasks, emphasizing current trends and illustrating a clear transition from classical to deep learning methods with existing datasets, divided by task and including statistics for each of them. As a result of this comprehensive review, we agree that the results demonstrate notable improvements. Still, there remain several key challenges like refining model robustness under varying environmental conditions, including diverse lighting and occlusion; adaptation to different camera angles; and ethical and legal issues related to privacy rights.

The use of event-based cameras in computer vision is a growing research direction. However, despite the existing research on face detection using the event camera, a substantial gap persists in the availability of a large dataset featuring annotations for faces and facial landmarks on event streams, thus hampering the development of applications in this direction. In this work, we address this issue by publishing the first large and varied dataset (Faces in Event Streams) with a duration of 689 min for face and facial landmark detection in direct event-based camera outputs. In addition, this article presents 12 models trained on our dataset to predict bounding box and facial landmark coordinates with an mAP₅₀ score of more than 90%. We also performed a demonstration of real-time detection with an event-based camera using our models.

Accurate face detection and subsequent localization of facial landmarks are mandatory steps in many computer vision applications, such as emotion recognition, age estimation, and gender identification. Thanks to advancements in deep learning, numerous facial applications have been developed for human faces. However, most have to employ multiple models to accomplish several tasks simultaneously. As a result, they require more memory usage and increased inference time. Also, less attention is paid to other domains, such as animals and cartoon characters. To address these challenges, we propose an input-agnostic face model, AnyFace++, to perform multiple face-related tasks concurrently. The tasks are face detection and prediction of facial landmarks for human, animal, and cartoon faces, including age estimation, gender classification, and emotion recognition for human faces. We trained the model using deep multi-task, multi-domain learning with a heterogeneous cost function. The experimental results demonstrate that AnyFace++ generates outcomes comparable to cutting-edge models designed for specific domains.

Deep learning-based approaches have achieved remarkable success in various image-based dietary assessment applications, including food detection and estimating portion sizes. However, most existing methods address these tasks separately, limiting their practical applicability in real-world scenarios where simultaneous processing is required. This study presents an end-to-end multi-task method that integrates food detection and portion size estimation within a single model, leveraging the state-of-the-art YOLOv12 architecture. To support this approach, this paper introduces the Food Portion Benchmark (FPB) dataset – a comprehensive and diverse collection comprising 14,083 images across 138 food classes, each with manually annotated bounding boxes and laboratory-measured component weights. To promote reproducibility and standardization, a public Food AI leaderboard has been deployed on Hugging Face, enabling researchers to benchmark their models for detection and weight estimation on the FPB dataset. In addition, this work provides pre-trained model weights and model-generated annotations, eliminating the need for researchers to perform their own resource-intensive measurements and annotations of food items. The proposed method achieves state-of-the-art performance, with a mean average precision (mAP50) of 0.978 for food detection and a mean absolute error (MAE) of only 90.95 grams for portion size estimation on the FPB test set. These results highlight the effectiveness and practicality of an integrated model for accurate and comprehensive dietary analysis. It is anticipated that this FPB dataset and its model will serve as a foundational reference for dietary assessment, particularly for culturally relevant foods in Central Asia.

Accurate face detection and subsequent localization of facial landmarks are mandatory in many computer vision applications, such as emotion recognition, age estimation, and gender identification. Thanks to advancements in deep learning, numerous applications were developed for human faces. However, many applications have to employ multiple models to accomplish various tasks. As a result, they require more memory usage and increased inference time. Also, less attention is paid to other domains, such as animals and cartoon characters. To address these challenges, we propose an input-agnostic face model, AnyFace++, to perform multiple face-related tasks concurrently. The tasks are face detection and prediction of facial landmarks for human, animal, and cartoon faces, as well as age estimation, gender classification, and emotion recognition for human faces. We trained the model using deep multi-task multi-domain learning with a heterogeneous cost function. The experimental results demonstrate that AnyFace++ generates outcomes comparable to those of cutting-edge models specifically designed for specific domains. We have made the source code and pre-trained model publicly available at https://github.com/IS2AI/AnyFacePP to bolster research in this area.

Apple jam is a widely used all-season product. The quality of the jam is closely related to its sugar concentration, which affects its taste, texture, shelf life, and legal compliance with production requirements. Although traditional methods for measuring sugar, such as titration, enzymatic methods, and chromatography, are accurate, they are also invasive, destructive, and unsuitable for rapid screening. This study investigates a non-destructive and non-invasive alternative method that uses hyperspectral imaging (HSI) in combination with machine learning to estimate the sugar content in processed apple products. Eight cultivars were selected from the Central Asian region, recognized as the origin of apples and known for its rich diversity of apple cultivars. A total of 88 jam samples were prepared with sugar concentrations ranging from 25% to 75%. For each sample, several hyperspectral images were obtained using a visible-to-near-infrared (VNIR) camera. The acquired spectral data were then processed and analyzed using regression models, including the support vector machine (SVM), eXtreme gradient boosting (XGBoost), and a one-dimensional residual network (1D ResNet). Among them, ResNet achieved the highest prediction accuracy of R² = 0.948. The results highlight the potential of HSI and machine learning for a fast, accurate, and non-invasive assessment of the sugar content in processed foods.