This paper discusses current methods and trends for 3D bounding box detection in volumetric medical image data. For this purpose, an overview of relevant papers from recent years is given. 2D and 3D implementations are discussed and compared and multiple identified approaches for localizing anatomical structures are presented. The results show that most research recently focuses on Deep Learning methods, such as Convolutional Neural Networks instead of methods with manual feature engineering, e.g., Random Regression Forests. 2D and 3D implementations are equally common. An overview of bounding box detection options is presented and helps researchers to select the most promising approach for their target objects.
The chicken is the world’s most farmed animal. In this work, we introduce the Chicks4FreeID dataset, the first publicly available dataset focused on the reidentification of individual chickens. We begin by providing a comprehensive overview of the existing animal reidentification datasets. Next, we conduct closed-set reidentification experiments on the introduced dataset, using transformer-based feature extractors in combination with two different classifiers. We evaluate performance across domain transfer, supervised, and one-shot learning scenarios. The results demonstrate that transfer learning is particularly effective with limited data, and training from scratch is not necessarily advantageous even when sufficient data are available. Among the evaluated models, the vision transformer paired with a linear classifier achieves the highest performance, with a mean average precision of 97.0%, a top-1 accuracy of 95.1%, and a top-5 accuracy of 100.0%. Our evaluation suggests that the vision transformer architecture produces higher-quality embedding clusters than the Swin transformer architecture. All data and code are publicly shared under a CC BY 4.0 license.
Image processing is becoming one of the key technologies of the fourth industrial revolution (4IR) which provides different ways of detecting and recognizing faces, persons and other objects in an image. This can benefit large archives with historical images such as the Robben Island Mayibuye Archives where many figures of the Apartheid struggle appearing in pictures are still unknown. This paper analyzes the findings of the first step of Archiving 4.0, a project that aims of using 4IR techniques to support and improve archiving in South Africa. It aims at finding the best among different models for face detection by evaluating their performance on a subset of the images from the Robben Island Mayibuye Archives. For a range of selected face detection models, the Intersection over Union and the Average Precision are calculated. The models are evaluated and compared on the basis of these metrics and their speed. The results show the strengths and weaknesses of the different approaches and reveal which of the approaches is best to be used in which situation.