ContexedNet: Context–Aware Ear Detection in Unconstrained Settings

Emeršič, Žiga; Sušanj, Diego; Meden, Blaž; Peer, Peter

doi:10.1109/access.2021.3121792

Cited by 22 publications

(6 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The first step in most Computer Vision systems is object or subject detection, where bounding boxes are used to identify the location of the desired object or subject within an image [6]. However, this technique is limited in that it only provides a rough estimate of the object's location [7]. To overcome this limitation, a more detailed technique called segmentation is also used, which labels each individual pixel as being a part of the object or the background.…”

Section: Learning Module 2: Detection and Segmentationmentioning

confidence: 99%

ROSUS 2023 - Računalniška obdelava slik in njena uporaba v Sloveniji 2023: Zbornik 17. strokovne konference

2023

View full text Add to dashboard Cite

the development group, Vision Lab Slovenia, is part of a global development team working in the field of autonomous perception. Industrial automation is changing at an extremely fast pace. As an innovation leader at the forefront of the development of state-of-the-art sensor technology, SICK today offers solutions that are ready for the challenges of the futurewith intelligent sensors that collect data, evaluate it in real time, adapt to their environment and communicate in the network. In this paper, solutions based on image processing technologies are presented in more detail. Approaches are highlighted that support modularity and flexibility concepts through software, giving users a high degree of flexibility in solutions for specific requirements.

show abstract

Section: Learning Module 2: Detection and Segmentationmentioning

confidence: 99%

ROSUS 2023 - Računalniška obdelava slik in njena uporaba v Sloveniji 2023: Zbornik 17. strokovne konference

2023

View full text Add to dashboard Cite

show abstract

“…Po standardni metodologiji ocenjevanja uporabljamo štiri merila uspešnosti za poročanje o uspešnosti za segmentacijske naloge, to so Jaccardov indeks IoU, natančnost, priklic in mera F1 (Rot, 2020;Emeršič, 2021).…”

Section: Metrike Uspešnostiunclassified

ROSUS 2022 - Računalniška obdelava slik in njena uporaba v Sloveniji 2022: Zbornik 16. strokovne konference

2022

View full text Add to dashboard Cite

Povzetek V zadnjem desetletju se je v Laboratoriju za računalniški vid na FRI UL oblikovala močna skupina, ki dela na področju biometrije. Skupina je močno povezana z Laboratorijem za strojno inteligenco na FE UL. Prvi ključni koraki so bili narejeni v okviru kompetenčnih centrov, kjer smo v oblaku naredili fuzijo modalnosti, obrazov in prstih odtisov. Vzporedno s tem se je odvijalo delo na razpoznavanju ljudi iz načina gibanja. Nato je delo na področju biometrije dobilo še dodaten zagon. Posvetili smo se povsem novi modalnosti uhljev, začeli delati na izzivu fotorealistične deidentifikacije obrazov, dodali beločnico, šarenico ter obočesno regijo kot naslednje tri sveže modalnosti. V zadnjem času se ukvarjamo tudi z detekcijo globokih ponaredkov, oceno pravilnega nošenja mask, virtualnim pomerjanjem oblačil, obdelavo prstnih sledi (latentov) in celovitim ohranjanjem zasebnosti obrazov. Na drugi stopnji študija smo uvedli tudi nov izbirni predmet Slikovna biometrija. Ta ima letos spet skoraj 90 slušateljev. Število članov skupine trenutno raste iz leta v leto, temu primerno tudi financiranje in publikacije na ključnih konferencah ter v revijah, nenazadnje pa se vpliv skupine pozna tudi pri organizaciji tekmovanj na teh konferencah ter tudi zmagah na sorodnih tekmovanjih. Predavanje bo osvetlilo prehojeno pot skozi ključne raziskovalne vsebine. Spletna stran: https://fri.uni-lj.si/sl/laboratorij/lrv.

show abstract

“…The ear segmentation performance is reported on the AWE dataset [26] and the corresponding performance figures for the average accuracy, the average IoU, the average precision, the average recall are 99.8 %, 84.8%, 91.7% and 91.6%, respectively. The most recent study related to ear semantic segmentation is Context-aware Ear Detection Network (ContexedNet) [31]. ContexedNet has two stages.…”

Section: Convolution Neural Network Based Approaches For Pixelwise Ea...mentioning

confidence: 99%

Ear semantic segmentation in natural images with Tversky loss function supported DeepLabv3+ convolutional neural network

Inan

Kacar

2022

Balkan Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

Semantic segmentation is a fundamental problem for computer vision. On the other hand, for studies in the field of biometrics, semantic segmentation is gaining more importance. Many successful biometric recognition systems require a high- performance semantic segmentation algorithm. In this study, we present an effective ear segmentation technique in natural images. A convolutional neural network is trained for pixel-based ear segmentation. DeepLab v3+ network structure, with ResNet-18 as the backbone and Tversky lost function layer as the last layer, has been trained with natural and uncontrolled images. We perform the proposed network training using only the 750 images in the Annotated Web Ears (AWE) training set. The corresponding tests are performed on the AWE Test Set, University of Ljubljana Test Set, and the Collection A of In-The-Wild dataset. For the Annotated Web Ears (AWE) dataset, intersection over union (IoU) is measured as 86.3% for the AWE database. To the best of our knowledge, this is the highest performance achieved among the algorithms tested on the AWE test set.

show abstract

ContexedNet: Context–Aware Ear Detection in Unconstrained Settings

Cited by 22 publications

References 57 publications

ROSUS 2023 - Računalniška obdelava slik in njena uporaba v Sloveniji 2023: Zbornik 17. strokovne konference

ROSUS 2023 - Računalniška obdelava slik in njena uporaba v Sloveniji 2023: Zbornik 17. strokovne konference

ROSUS 2022 - Računalniška obdelava slik in njena uporaba v Sloveniji 2022: Zbornik 16. strokovne konference

Ear semantic segmentation in natural images with Tversky loss function supported DeepLabv3+ convolutional neural network

Contact Info

Product

Resources

About