This paper tackles the supervised evaluation of image segmentation and object proposal algorithms. It surveys, structures, and deduplicates the measures used to compare both segmentation results and object proposals with a ground truth database; and proposes a new measure: the precision-recall for objects and parts. To compare the quality of these measures, eight state-of-the-art object proposal techniques are analyzed and two quantitative meta-measures involving nine state of the art segmentation methods are presented. The meta-measures consist in assuming some plausible hypotheses about the results and assessing how well each measure reflects these hypotheses. As a conclusion of the performed experiments, this paper proposes the tandem of precision-recall curves for boundaries and for objects-and-parts as the tool of choice for the supervised evaluation of image segmentation. We make the datasets and code of all the measures publicly available.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TPAMI.2015.2481406 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A pupillary image dataset: 10,000 annotated and 258,790 non-annotated images of patients with glaucoma, diabetes, and subjects influenced by alcohol, coupled with a segmentation performance evaluation.
Comput Biol Med
January 2025
Institute of Informatics, Federal University of Goiás, GO, Brazil.
The Pupillary Light Reflex (PLR) is the involuntary movement of the pupil adapting to lighting conditions. The measurement and qualification of this information have a broad impact in different fields. Thanks to technological advancements and algorithms, obtaining accurate and non-invasive records of pupillary movements is now possible, expanding practical applications.
View Article and Find Full Text PDFLanguage, theory of mind and cognitive skills in Arabic-speaking children with and without autism: Evidence from network and cluster analyses.
J Commun Disord
November 2024
Department of English Literature and Linguistics, Bar-Ilan University, Israel; Gonda Multidisciplinary Brain Research Center, Bar-Ilan University, Israel. Electronic address:
Introduction: Autism spectrum disorder (ASD) is characterized by impairments in social interactions, social communication, and repetitive and stereotyped patterns of behavior. Previous studies have reported mixed findings regarding the links between language (i.e.
View Article and Find Full Text PDFTraining Community Clinicians in Implementing CBT-ERP for Youth with OCD: A Pilot Study in Australian Community Mental Health Services.
Child Psychiatry Hum Dev
January 2025
School of Applied Psychology, Griffith University, Gold Coast, QLD, Australia.
This pilot study evaluated the outcomes associated with a training workshop in cognitive-behavioural therapy with exposure and response prevention (ERP) for youth with obsessive-compulsive disorder (OCD) aimed at improving clinicians' capabilities and motivations. Questionnaires and role-plays were completed by 17 Australian clinicians working across community youth (i.e.
View Article and Find Full Text PDFOptimizing Virtual Follow-Up Care: Realist Evaluation of Experiences and Perspectives of Patients With Breast and Prostate Cancer.
J Med Internet Res
January 2025
Cancer Rehabilitation and Survivorship, Department of Supportive Care, Princess Margaret Cancer Centre, Toronto, ON, Canada.
Background: Virtual follow-up (VFU) has the potential to enhance cancer survivorship care. However, a greater understanding is needed of how VFU can be optimized.
Objective: This study aims to examine how, for whom, and in what contexts VFU works for cancer survivorship care.
Object detection in motion management scenarios based on deep learning.
PLoS One
January 2025
School of Physical Education, Jinjiang College, Sichuan University, Chengdu, Sichuan Province, People's Republic of China.
In athletes' competitions and daily training, in order to further strengthen the athletes' sports level, it is usually necessary to analyze the athletes' sports actions at a specific moment, in which it is especially important to quickly and accurately identify the categories and positions of the athletes, sports equipment, field boundaries and other targets in the sports scene. However, the existing detection methods failed to achieve better detection results, and the analysis found that the reasons for this phenomenon mainly lie in the loss of temporal information, multi-targeting, target overlap, and coupling of regression and classification tasks, which makes it more difficult for these network models to adapt to the detection task in this scenario. Based on this, we propose for the first time a supervised object detection method for scenarios in the field of motion management.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!