A Realistic Hand Image Composition Method for Palmprint ROI Embedding Attack

Deep learning has become the main way of the object detection task for autonomous vehicles. Meanwhile, this method typically requires vast amounts of training data to reach their full potential. However, collecting the data from real world and labeling manually is an expensive, time-consuming and error-prone process. Synthetic image has the potential to replace real image for training neural networks, because image creation and labeling annotations are free in this way. For the network trained by synthetic images, the reality gap between real and synthetic images is the main obstacle to use it in the real world. And most previous works are only devoted to generate synthetic images with a good performance on model training, but lack of analysis of the domain gap that affects the performance. This work designs a method of generating the real and synthetic images to analyze and reduce the reality gap between synthetic and real images for car detection. Firstly, this work put one single car with no-background in a random background image to generate real single car and synthetic single car images. In order to further reduce the domain gap in content level, this method keeps the car distribution in synthetic images is similar with the distribution of car in real world. For the purpose of reducing the domain gap in appearance level, the parameters of camera model are same as the camera parameters of image collecting cars and the image is rendered by using the PBRT(Physically Based Ray Tracing) when we generated the synthetic images. Secondly, by training the neural network of instance segmentation with different datasets, the across validation result proves that the reality gap between synthetic and real images is no more than the domain gap between real images. Thirdly, the training results of datasets with different samples diversity show that the diversity of the samples yields better generalization between different datasets for car detection which can effectively reduce the domain gap.

Chest radiography is one of the most ubiquitous imaging modalities, playing an essential role in screening, diagnosis and disease management. However, chest radiography interpretation is a time-consuming and complex task, requiring the availability of experienced radiologists. As such, automated diagnosis systems for pathology detection have been proposed aiming to reduce the burden on radiologists and reduce variability in image interpretation. While promising results have been obtained, particularly since the advent of deep learning, there are significant limitations in the developed solutions, namely the lack of representative data for less frequent pathologies and the learning of biases from the training data, such as patient position, medical devices and other markers as proxies for certain pathologies. The lack of explainability is also a challenge for the adoption of these solutions in clinical practice.Generative adversarial networks could play a significant role as a solution for these challenges as they allow to artificially create new realistic images. This way, new synthetic chest radiography images could be used to increase the prevalence of less represented pathology classes and decrease model biases as well as improving the explainability of automatic decisions by generating samples that serve as examples or counter-examples to the image being analysed, ensuring patient privacy.In this study, a few-shot generative adversarial network is used to generate synthetic chest radiography images. A minimum Fréchet Inception Distance score of 17.83 was obtained, allowing to generate convincing synthetic images. Perceptual validation was then performed by asking multiple readers to classify a mixed set of synthetic and real images. An average accuracy of 83.5% was obtained but a strong dependency on reader experience level was observed. While synthetic images showed structural irregularities, the overall image sharpness was a major factor in the decision of readers. The synthetic images were then validated using a MobileNet abnormality classifier and it was shown that over 99% of images were classified correctly, indicating that the generated images were correctly interpreted by the classifier. Finally, the use of the synthetic images during training of a YOLOv5 pathology detector showed that the addition of the synthetic images led to an improvement of mean average precision of 0.05 across 14 pathologies.In conclusion, the usage of few-shot generative adversarial networks for chest radiography image generation was shown and tested in multiple scenarios, establishing a baseline for future experiments to increase the applicability of generative models in clinical scenarios of automatic CXR screening and diagnosis tools.

Palmprints have been broadly used for personal authentication because they are highly accurate and incur low cost. Most previous works have focused on two-dimensional (2-D) palmprint recognition in the past decade. Unfortunately, 2-D palmprint recognition systems lose the shape information when capturing palmprint images. Moreover, such 2-D palmprint images can be easily forged or affected by noise. Hence, three-dimensional (3-D) palmprint recognition has been regarded as a promising way to further improve the performance of palmprint recognition systems. We have developed a simple, but efficient method for 3-D palmprint recognition by using local features. We first utilize shape index representation to describe the geometry of local regions in 3-D palmprint data. Then, we extract local binary pattern and Gabor wavelet features from the shape index image. The two types of complementary features are finally fused at a score level for further improvements. The experimental results on the Hong Kong Polytechnic 3-D palmprint database, which contains 8000 samples from 400 palms, illustrate the effectiveness of the proposed method.

Large annotated datasets are required for training deep learning models, but in medical imaging data sharing is often complicated due to ethics, anonymization and data protection legislation. Generative AI models, such as generative adversarial networks (GANs) and diffusion models, can today produce very realistic synthetic images, and can potentially facilitate data sharing. However, in order to share synthetic medical images it must first be demonstrated that they can be used for training different networks with acceptable performance. Here, we therefore comprehensively evaluate four GANs (progressive GAN, StyleGAN 1–3) and a diffusion model for the task of brain tumor segmentation (using two segmentation networks, U-Net and a Swin transformer). Our results show that segmentation networks trained on synthetic images reach Dice scores that are 80%–90% of Dice scores when training with real images, but that memorization of the training images can be a problem for diffusion models if the original dataset is too small. Our conclusion is that sharing synthetic medical images is a viable option to sharing real images, but that further work is required. The trained generative models and the generated synthetic images are shared on AIDA data hub.

Gender prediction from hand or face images is relevant in domains where only one modality may be available, such as security, healthcare, or assistive technologies. Existing approaches typically require separate models for each modality, increasing complexity and limiting flexibility. This work introduces a unified deep learning framework for gender prediction that operates on either hand or face inputs without retraining. Two complementary architectures are proposed: a Unified Modality-Conditioned Classifier (UMCC), which integrates modality tags into shared features, and a Modality-Aware Gated (MAG) network, which learns internal routing to specialized heads. Evaluation is conducted on a curated corpus of 15,064 aligned hand–face pairs with subject-exclusive splits, standardized labeling, and transparent protocols. The best configuration, based on EfficientNetV2-S, achieves competitive accuracy on the in-domain test set (91.0% [95% CI: 90.2–91.7]), with higher performance on faces (95.8%) and reasonably good performance on hands (84.8%). Cross-dataset testing on FairFace, UTKFace, and 11K Hands datasets indicates that the unified model retains competitive performance under domain shift, while fairness analysis across apparent-race groups reveals non-trivial disparities that can be partially mitigated through threshold calibration. These findings show that a single unified model, instantiated as UMCC or MAG, delivers performance comparable to modality-specific systems while reducing deployment and auditing complexity. Limitations include some variability on hand images and observed disparities across demographic subgroups. Future extensions may incorporate additional biometric modalities (e.g., iris, voice, gait) and investigate lightweight adapters and adaptive calibration strategies to further enhance robustness and equity.

In the past, people usually employ the facial feature extraction and shallow learners such as decision trees, SVM, Naive Bayes, etc. to classify faces of different races. Deep learning usually takes lots of time to train. But with the advances in hardware and new algorithm proposed, the training time problem is gradually alleviated. The deep convolutional neural networks have good effect on images classification. In this paper, we use the deep convolutional neural networks to try to solve the problem of classification faces of different racial origin. Because the convolutional neural networks usually require a huge amount of data for training for good performance, such training set of real racial faces is not available to us. As a result of small set of real racial faces, this study proposes to incorporate synthetic facial images in our training set to sufficiently increase the size of the training set. To the best of our knowledge, this study is the first to propose to incorporate synthetic racial faces to train a deep convolutional neural network to classify real racial faces. We compare the performance of only employ synthetic facial images and mixtures of synthetic and real facial images in the training set. Our experiments show that training with only the real facial images (2,500 images) can achieve 91.25% accuracy in classifying faces of three different race origins. However, the classification when training with a mixture of 2,500 real facial images and 15,000 synthetic facial images can be further improved to 98.5% in accuracy.

PurposeTo develop generative adversarial networks (GANs) that synthesize realistic anterior segment optical coherence tomography (AS-OCT) images and evaluate deep learning (DL) models that are trained on real and synthetic datasets for detecting angle closure.MethodsThe GAN architecture was adopted and trained on the dataset with AS-OCT images collected from the Joint Shantou International Eye Center of Shantou University and the Chinese University of Hong Kong, synthesizing open- and closed-angle AS-OCT images. A visual Turing test with two glaucoma specialists was performed to assess the image quality of real and synthetic images. DL models, trained on either real or synthetic datasets, were developed. Using the clinicians’ grading of the AS-OCT images as the reference standard, we compared the diagnostic performance of open-angle vs. closed-angle detection of DL models and the AS-OCT parameter, defined as a trabecular-iris space area 750 µm anterior to the scleral spur (TISA750), in a small independent validation dataset.ResultsThe GAN training included 28,643 AS-OCT anterior chamber angle (ACA) images. The real and synthetic datasets for DL model training have an equal distribution of open- and closed-angle images (all with 10,000 images each). The independent validation dataset included 238 open-angle and 243 closed-angle AS-OCT ACA images. The image quality of real versus synthetic AS-OCT images was similar, as assessed by the two glaucoma specialists, except for the scleral spur visibility. For the independent validation dataset, both DL models achieved higher areas under the curve compared with TISA750. Two DL models had areas under the curve of 0.97 (95% confidence interval, 0.96–0.99) and 0.94 (95% confidence interval, 0.92–0.96).ConclusionsThe GAN synthetic AS-OCT images appeared to be of good quality, according to the glaucoma specialists. The DL models, trained on all-synthetic AS-OCT images, can achieve high diagnostic performance.Translational RelevanceThe GANs can generate realistic AS-OCT images, which can also be used to train DL models.

A major challenge in applying deep learning to medical imaging is the paucity of annotated data. This study explores the use of synthetic images for data augmentation to address the challenge of limited annotated data in colonoscopy lesion classification. We demonstrate that synthetic colonoscopy images generated by Generative Adversarial Network (GAN) inversion can be used as training data to improve polyp classification performance by deep learning models. We invert pairs of images with the same label to a semantically rich and disentangled latent space and manipulate latent representations to produce new synthetic images. These synthetic images maintain the same label as the input pairs. We perform image modality translation (style transfer) between white light and narrow-band imaging (NBI). We also generate realistic synthetic lesion images by interpolating between original training images to increase the variety of lesion shapes in the training dataset. Our experiments show that GAN inversion can produce multiple colonoscopy data augmentations that improve the downstream polyp classification performance by 2.7% in F1-score and 4.9% in sensitivity over other methods, including state-of-the-art data augmentation. Testing on unseen out-of-domain data also showcased an improvement of 2.9% in F1-score and 2.7% in sensitivity. This approach outperforms other colonoscopy data augmentation techniques and does not require re-training multiple generative models. It also effectively uses information from diverse public datasets, even those not specifically designed for the targeted downstream task, resulting in strong domain generalizability. Project code and model: https://github.com/DurrLab/GAN-Inversion.

Text-to-image generation models have achieved remarkable advancements in recent years, aiming to produce realistic images from textual descriptions. However, these models often struggle with generating anatomically accurate representations of human hands. The resulting images frequently exhibit issues such as incorrect numbers of fingers, unnatural twisting or interlacing of fingers, or blurred and indistinct hands. These issues stem from the inherent complexity of hand structures and the difficulty in aligning textual descriptions with precise visual depictions of hands. To address these challenges, we propose a novel approach named Hand1000 that enables the generation of realistic hand images with target gesture using only 1,000 training samples. The training of Hand1000 is divided into three stages with the first stage aiming to enhance the model’s understanding of hand anatomy by using a pre-trained hand gesture recognition model to extract gesture representation. The second stage further optimizes text embedding by incorporating the extracted hand gesture representation, to improve alignment between the textual descriptions and the generated hand images. The third stage utilizes the optimized embedding to fine-tune the Stable Diffusion model to generate realistic hand images. In addition, we construct the first publicly available dataset specifically designed for text-to-hand image generation. Based on the existing hand gesture recognition dataset, we adopt advanced image captioning models and LLaMA3 to generate high-quality textual descriptions enriched with detailed gesture information. Extensive experiments demonstrate that Hand1000 significantly outperforms existing models in producing anatomically correct hand images while faithfully representing other details in the text, such as faces, clothing and colors.

We present an Automatic License Plate Recognition system designed around Convolutional Neural Networks (CNNs) and trained over synthetic plate images. We first design CNNs suitable for plate and character detection, sharing a common architecture and training procedure. Then, we generate synthetic images that account for the varying illumination and pose conditions encountered with real plate images and we use exclusively such synthetic images to train our CNNs. Experiments with real vehicle images captured in natural light with commodity imaging systems show precision and recall in excess of 93% despite our networks are trained exclusively on synthetic images.

An unsupervised domain adaptation scheme for single-stage artwork recognition in cultural sites

Image synthesis in magnetic resonance (MR) imaging has been an active area of research for more than ten years. MR image synthesis can be used to create images that were not acquired or replace images that are corrupted by artifacts, which can be of great benefit in automatic image analysis. Although synthetic images have been used with success in many applications, it is quite often true that they do not look like real images. In practice, an expert can usually distinguish synthetic images from real ones. Generative adversarial networks (GANs) have significantly improved the realism of synthetic images. However, we argue that further improvements can be made through the introduction of noise in the synthesis process, which better models the actual imaging process. Accordingly, we propose a novel approach that incorporates randomness into the model in order to better approximate the distribution of real MR images. Results show that the proposed method has comparable accuracy with the state-of-the-art approaches as measured by multiple similarity measurements while also being able to control the noise level in synthetic images. To further demonstrate the superiority of this model, we present results from a human observer study on synthetic images, which shows that our results capture the essential features of real MR images.

We consider the problem of object segmentation in cultural sites. Since collecting and labeling large datasets of real images is challenging, we investigate whether the use of synthetic images can be useful to achieve good segmentation performance on real data. To perform the study, we collected a new dataset comprising both real and synthetic images of 24 artworks in a cultural site. The synthetic images have been automatically generated from the 3D model of the considered cultural site using a tool developed for that purpose. Real and synthetic images have been labeled for the task of semantic segmentation of artworks. We compare three different approaches to perform object segmentation exploiting real and synthetic data. The experimental results point out that the use of synthetic data helps to improve the performances of segmentation algorithms when tested on real images. Satisfactory performance is achieved exploiting semantic segmentation together with image-to-image translation and including a small amount of real data during training. To encourage research on the topic, we publicly release the proposed dataset at the following url: https://iplab.dmi.unict.it/EGO-CH-OBJ-SEG/

This paper presents an ablation study aimed at investigating the impact of a hybrid dataset, domain randomisation, and custom-designed neural network architecture on the performance of object localisation. In this regard, real images were gathered from the Boeing 737-400 aircraft while synthetic images were generated using the domain randomisation technique involved randomising various parameters of the simulation environment in a photo-realistic manner. The study results indicated that the use of the hybrid dataset, domain randomisation, and the custom-designed neural network architecture yielded a significant enhancement in object localisation performance. Furthermore, the study demonstrated that domain randomisation facilitated the reduction of the reality gap between the real-world and simulation environments, leading to a better generalisation of the neural network architecture on real-world data. Additionally, the ablation study delved into the impact of each randomisation parameter on the neural network architecture’s performance. The insights gleaned from this investigation shed light on the importance of each constituent component of the proposed methodology and how they interact to enhance object localisation performance. The study affirms that deploying a hybrid dataset, domain randomisation, and custom-designed neural network architecture is an effective approach to training deep neural networks for object localisation tasks. The findings of this study can be applied to a wide range of computer vision applications, particularly in scenarios where collecting large amounts of labelled real-world data is challenging. The study employed a custom-designed neural network architecture that achieved 99.19% accuracy, 98.26% precision, 99.58% recall, and 97.92% mAP@.95 trained using a hybrid dataset comprising synthetic and real images.

Image segmentation has recently become an essential step in image processing as it mainly conditions the interpretation which is done afterwards. It is still difficult to justify the accuracy of a segmentation algorithm, regardless of the nature of the treated image. In this paper we perform an objective comparison of region-based segmentation techniques such as supervised and unsupervised deterministic classification, non-parametric and parametric probabilistic classification. Eight methods among the well-known and used in the scientific community have been selected and compared. The Martin's(GCE, LCE), probabilistic Rand Index (RI), Variation of Information (VI) and Boundary Displacement Error (BDE) criteria are used to evaluate the performance of these algorithms on Magnetic Resonance (MR) brain images, synthetic MR image, and synthetic images. MR brain image are composed of the gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF) and others, and the synthetic MR image composed of the same for real image and the plus edema, and the tumor. Results show that segmentation is an image dependent process and that some of the evaluated methods are well suited for a better segmentation. Keywords—Evaluation criteria; Martin's; Rand Index; Image Segmentation; Magnetic resonance image. I. INTRODUCTION