Relevance Feedback in Biometric Retrieval of Animal Photographs

Finn, Chelsea; Duyck, James; Hutcheon, Andy; Vera, Pablo; Salas, Joaquín; Ravela, Sai

doi:10.1007/978-3-319-07491-7_29

Cited by 9 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SIFT features can also be improved in a number of ways to deal with nonlinear deformations, for example in Sloop by using them as a precursor to scale-cascaded alignment [9] or by randomized perturbations of the image geometry [1,10]. Here, the role of relevance feedback is explored with other established techniques SIFT, SURF and ORB, extending recent work [10,23]. This paper is the first detailed presentation including a streamlined architecture and comparative and exhaustive experiments on all species data.…”

Section: Related Workmentioning

confidence: 98%

Sloop: A pattern retrieval engine for individual animal identification

Duyck

Finn

Hutcheon³

et al. 2015

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 98%

Sloop: A pattern retrieval engine for individual animal identification

Duyck

Finn

Hutcheon³

et al. 2015

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

“…Relevance feedback was then introduced [14,18], as were example-based specularity removal [19] and segmentation methods. Following a redesign of the Sloop system, by 2012, we incorporated crowdsourced relevance feedback [16,4], and ingested randomized representations, hybrid contexts into the available routines for creating workflows. Embedded systems versions of Sloop emerged (cellphones, autonomous systems) along with operational use [3] that demonstrated large-scale successes [20].…”

Section: Developments Leading To Sloopmentioning

confidence: 99%

The Sloop System for Individual Animal Identification with Deep Learning

Bakliwal,

Ravela

2020

Preprint

Self Cite

View full text Add to dashboard Cite

The Sloop system indexes and retrieves photographs of non-stationary animal population distributions. To do this, it adaptively represents and matches generic visual feature representations using sparse relevance feedback from experts and crowds. Here, we describe the Sloop system and its application, then compare its approaches to standard deep learning formulations. Results suggest that some of the key ideas that enable Sloop's performance may also benefit deep learning approaches to individual identification.

show abstract

“…Recently, advances in computer-vision techniques combined with animals' unique characteristics, animal biometrics, have introduced a more effective and non-invasive approach to recognize animal individuals. These approaches rely on largescale datasets and involve manual or semi-manual work to identify individuals [6][7][8].…”

Section: Introductionmentioning

confidence: 99%

An Automated Framework Based on Deep Learning for Shark Recognition

Moon

Lowe

et al. 2022

JMSE

View full text Add to dashboard Cite

The recent progress in deep learning has given rise to a non-invasive and effective approach for animal biometrics. These modern techniques allow researchers to track animal individuals on a large-scale image database. Typical approaches are suited to a closed-set recognition problem, which is to identify images of known objects only. However, such approaches are not scalable because they mis-classify images of unknown objects. To recognize the images of unknown objects as ‘unknown’, a framework should be able to deal with the open set recognition scenario. This paper proposes a fully automatic, vision-based identification framework capable of recognizing shark individuals including those that are unknown. The framework first detects and extracts the shark from the original image. After that, we develop a deep network to transform the extracted image to an embedding vector in latent space. The proposed network consists of the Visual Geometry Group-UNet (VGG-UNet) and a modified Visual Geometry Group-16 (VGG-16) network. The VGG-UNet is utilized to detect shark bodies, and the modified VGG-16 is used to learn embeddings of shark individuals. For the recognition task, our framework learns a decision boundary using a one-class support vector machine (OSVM) for each shark included in the training phase using a few embedding vectors belonging to them, then it determines whether a new shark image is recognized as belonging to a known shark individual. Our proposed network can recognize shark individuals with high accuracy and can effectively deal with the open set recognition problem with shark images.

show abstract

Relevance Feedback in Biometric Retrieval of Animal Photographs

Cited by 9 publications

References 16 publications

Sloop: A pattern retrieval engine for individual animal identification

Sloop: A pattern retrieval engine for individual animal identification

The Sloop System for Individual Animal Identification with Deep Learning

An Automated Framework Based on Deep Learning for Shark Recognition

Contact Info

Product

Resources

About