The paper provides a comprehensive overview of the state-of-the-art in affine covariant region detectors and compares their performance on a set of test images under various imaging conditions. Six types of detectors are included: Harris-Affine, Hessian-Affine, Maximally Stable Extremal Regions (MSER), edge-based regions, intensity extrema-based regions, and salient regions. The performance is evaluated against changes in viewpoint, scale, illumination, defocus, and image compression. The paper aims to establish a reference test set and performance software to facilitate future evaluations of affine covariant region detectors. The detectors are described in detail, and their repeatability and distinctiveness are assessed using overlap measures and the SIFT descriptor. The results highlight the strengths and limitations of each detector, providing insights into their robustness and effectiveness under different transformations.The paper provides a comprehensive overview of the state-of-the-art in affine covariant region detectors and compares their performance on a set of test images under various imaging conditions. Six types of detectors are included: Harris-Affine, Hessian-Affine, Maximally Stable Extremal Regions (MSER), edge-based regions, intensity extrema-based regions, and salient regions. The performance is evaluated against changes in viewpoint, scale, illumination, defocus, and image compression. The paper aims to establish a reference test set and performance software to facilitate future evaluations of affine covariant region detectors. The detectors are described in detail, and their repeatability and distinctiveness are assessed using overlap measures and the SIFT descriptor. The results highlight the strengths and limitations of each detector, providing insights into their robustness and effectiveness under different transformations.