Small Hand-held Object Recognition Test (SHORT)

Rivera-Rubio, Jose; Idrees, Saad; Alexiou, Ioannis; Hadjilucas, Lucas; Bharath, Anil A.

doi:10.1109/wacv.2014.6836057

Cited by 11 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Rivera-Rubio et al [9] alcanc ¸aram 77,51% de acurácia média no conjunto ST-SG e 69,41% no conjunto VF-SG. Os autores não relataram os desvios padrões das acurácias médias.…”

Section: A Resultados Com a Short-100unclassified

“…Rivera-Rubio et al [9] propuseram três abordagens: (1) Scale-Invariant Feature Transform (SIFT) + K-Means + Support Vector Machine (SVM) ; (2) SIFT + Locality-constrained Linear Coding (LLC) ; e (3) SIFT + Principal Component Analysis (PCA) + Fisher Vector Encoding + SVM. O artigo introduziu a base de dados SHORT-100.…”

Section: Trabalhos Relacionadosmentioning

confidence: 99%

“…1) SHORT-100: Rivera-Rubio et al [9] desenvolveram a base de dados SHORT-100, com conjuntos de treino e teste definidos. Inicialmente, a base era chamada de SHORT-30, pois possuía apenas 30 classes de produtos.…”

Section: A Bases De Dadosunclassified

See 2 more Smart Citations

Grocery Product Recognition to Aid Visually Impaired People

Machado¹,

Aires²,

Veras³

et al. 2021

Anais Do XVII Workshop De Visão Computacional (WVC 2021)

View full text Add to dashboard Cite

This paper proposes a new approach in object recognition to assist visually impaired people. This approach achieved accuracy rates higher than the approaches proposed by the authors of the selected datasets. We applied Data Augmentation with other techniques and adjustments to different Pre-trained CNNs (Convolutional Neural Networks). The ResNet-50 based approach achieved the best results in the most recent datasets. This work focused on products that are usually found on grocery store shelves, supermarkets, refrigerators or pantries.

show abstract

“…Rivera-Rubio et al [9] alcanc ¸aram 77,51% de acurácia média no conjunto ST-SG e 69,41% no conjunto VF-SG. Os autores não relataram os desvios padrões das acurácias médias.…”

Section: A Resultados Com a Short-100unclassified

Section: Trabalhos Relacionadosmentioning

confidence: 99%

See 1 more Smart Citation

Grocery Product Recognition to Aid Visually Impaired People

Machado¹,

Aires²,

Veras³

et al. 2021

Anais Do XVII Workshop De Visão Computacional (WVC 2021)

View full text Add to dashboard Cite

show abstract

“…Previous studies on hand-held object recognition are focused on first-person (egocentric) interfaces [14][15] . Thus here we distinguish between first-person and second-person interfaces.…”

Section: Hand-held Object Recognitionmentioning

confidence: 99%

“…Note that in this case the user previews the image and can interactively control the camera and the object to optimize the coverage and the quality of the image, and minimize hand occlusion. The Small Hand-Held Object Recognition Test (SHORT) [14] focuses on this case. Another dataset including hand-held objects captured from a first-person point of view is Text-IVu [15] .…”

Section: Hand-held Object Recognitionmentioning

confidence: 99%

RGB-D Hand-Held Object Recognition Based on Heterogeneous Feature Fusion

Xiong

Jiang

Herranz

et al. 2015

J. Comput. Sci. Technol.

View full text Add to dashboard Cite

Object recognition has many applications in human-machine interaction and multimedia retrieval. However, due to large intra-class variability and inter-class similarity, accurate recognition relying only on RGB data is still a big challenge. Recently, with the emergence of inexpensive RGB-D devices, this challenge can be better addressed by leveraging additional depth information. A very special yet important case of object recognition is hand-held object recognition, as manipulating objects with hands is common and intuitive in human-human and human-machine interactions. In this paper, we study this problem and introduce an effective framework to address it. This framework first detects and segments the hand-held object by exploiting skeleton information combined with depth information. In the object recognition stage, this work exploits heterogeneous features extracted from different modalities and fuses them to improve the recognition accuracy. In particular, we incorporate handcrafted and deep learned features and study several multi-step fusion variants. Experimental evaluations validate the effectiveness of the proposed method.

show abstract