Zsolt Vörösházi

Zsolt Vörösházi

Auto-generated profile, based on publicly available information

Zsolt Vörösházi

Image Processing Research Laboratory, University of Pannonia, Veszprém, Hungary

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 November 2024 in IET Image Processing
Verified
Journal Article
Open access
RRRichárd Rádli
Richárd Rádli
ZVZsolt Vörösházi
Zsolt Vörösházi
LCLászló Czúni
László Czúni
Pill image recognition by machine vision can reduce the risk of taking the wrong medications, a severe healthcare problem. Automated dispensing machines or home applications both need reliable image processing techniques to compete with the problem of changing viewing conditions, large number of classes, and the similarity in pill appearance. The problem is attacked with a multi‐stream, two‐phase metric embedding neural model. To enhance the metric learning procedure, dynamic margin setting is introduced into the loss function. Moreover, it is shown that besides the visual features of drug samples, even free text of drug leaflets (processed with a natural language model) can be used to set the value of the margin in the triplet loss and thus increase the recognition accuracy of testing. Thus, besides using the conventional metric learning approach, the given discriminating features can be explicitly injected into the metric model using the NLP of the free text of pill leaflets or descriptors of images of selected pills. The performance on two datasets is analysed and a 1.6% (two‐sided) and 2.89% (one‐sided) increase in Top‐1 accuracy on the CURE dataset is reported compared to existing best results. The inference time on CPU and GPU makes the proposed model suitable for different kinds of applications in medical pill verification; moreover, the approach applies to other areas of object recognition where few‐shot problems arise. The proposed high‐level feature injection method (into a low‐level metric learning model) can also be exploited in other cases, where class features can be well described with textual or visual cues.

10 April 2026 in JMIR Medical Informatics
Verified
Journal Article
Open access
AAAmir Reza Ashraf
Amir Reza Ashraf
RRRichárd Rádli
Richárd Rádli
ZVZsolt Vörösházi
Zsolt Vörösházi
András FittlerAndrás Fittler
András Fittler
Background: Visual identification and verification of medications during dispensing and administration are prone to human error, particularly in high-pressure and high-volume clinical settings. Misidentification can lead to medication errors, posing risks to patient safety and placing a burden on health care systems. Recent advances in computer vision and object detection offer promising solutions for automated solid oral dosage form (pill) recognition. However, comprehensive studies comparing code-based and no-code (automated machine learning [AutoML]) approaches for pill recognition are lacking. Objective: This study aimed to evaluate and compare the performance, cost, usability, and deployment feasibility of pill recognition models developed with Ultralytics YOLO11 and 3 cloud-based AutoML platforms (Amazon Rekognition Custom Labels, Google Vertex artificial intelligence [AI] AutoML Vision, and Microsoft Azure Custom Vision) using multiple datasets, including real-world clinical images. Methods: Five training subsets of increasing size (1230, 3450, 7380, 14,400, and 26,880 images) from 30 commonly dispensed medications were used to train models on YOLO11 and 3 AutoML platforms. Models were evaluated on 6 datasets from different environments: clinical images from 3 hospitals, a verification dataset, a laboratory dataset, and an exhaustive testing set. Performance metrics, including accuracy, precision, recall, and mean average precision, were calculated. We evaluated the impact of training data size on performance and benchmarked training time, platform costs, and limitations. Results: No single platform dominated across all test environments. On the verification dataset (optimal conditions), accuracy ranged from 80.83% (YOLO11) to 91.60% (Google Vertex AI) when trained with the full training dataset. YOLO11 showed consistent performance improvement with increasing training data (accuracy: 63.06%-80.83%) and achieved near-perfect precision and mean average precision scores (0.95‐1.00). Google Vertex AI reached above 90% accuracy on 3 training subsets but showed unpredictable declines. Amazon Rekognition maintained near-perfect precision (0.92‐1.00) but had the highest false negative rates (up to 0.74), missing many pills. Custom Vision demonstrated steady performance improvements (77.08%-85.62% accuracy) but lagged behind other AutoML platforms, probably due to its older YOLOv2-based architecture. On clinical datasets, accuracy fluctuated (20.62%-90%) depending on the dataset and platform. Training costs and time varied: YOLO11 (open-source), Microsoft Azure (US $9.50-US $28.60, allowed user-predefined training duration), Google Vertex AI (US $69.30 with consistent 2.5‐3-hour training times), and Amazon Rekognition (US $5.43-US $43.89 with size-dependent training time scaling, reaching nearly 40 hours on the full 26,880-image dataset). Conclusions: Each platform offers distinct advantages and trade-offs: YOLO11 provides the highest flexibility and lowest platform costs but requires technical expertise, while AutoML platforms can offer high performance at a higher cost but with limited user control, introducing unpredictability. The performance variations demonstrate that successful clinical deployment requires careful platform selection based on specific performance requirements, budget constraints, and available technical resources, followed by rigorous validation using real-world, representative data to ensure patient safety in clinical workflows.