PFID: Pittsburgh fast-food image dataset

Chen, Mei; Dhingra, Kapil Dev; Wu, Wen; Yang, Lei; Sukthankar, Rahul; Yang, Jie

doi:10.1109/icip.2009.5413511

Cited by 214 publications

(138 citation statements)

References 9 publications

Supporting

Mentioning

137

Contrasting

Order By: Relevance

“…The collection is applicable to the problem at hand because it contains clusters of similar images, for example for outdoor environments, while maintaining a very broad category, in contrast to other datasets which are either too specific or too general (Toet et al, 2001;Deng et al, 2009;Chen et al, 2009). Indoor surroundings with similar characteristics can also be found, so we were able to identify similar images from this set.…”

Section: Applicationmentioning

confidence: 85%

Image Similarity Search using a Negative Selection Algorithm

Keijzers¹,

Maandag²,

Marchiori

et al. 2013

Advances in Artificial Life, ECAL 2013

View full text Add to dashboard Cite

The Negative Selection Algorithm is an immune inspired algorithm that can be used for different purposes such as fault detection, data integrity protection and virus detection. In this paper we show how the Negative Selection Algorithm can be adapted to tackle the similar image search problem: given a target image, images from a large database similar to the query have to be detected. Results of our experimental analysis indicate that the proposed algorithm is capable of detecting images similar to a target (self) image, given the right detectors. Source code and data used in the experiments are available on request.

show abstract

Section: Applicationmentioning

confidence: 85%

Image Similarity Search using a Negative Selection Algorithm

Keijzers¹,

Maandag²,

Marchiori

et al. 2013

Advances in Artificial Life, ECAL 2013

View full text Add to dashboard Cite

show abstract

“…ColourH [28] 11.3% OM [28] 28.2% BoW [27] 30.6% PRICoLBP [29] 45.4% SIFT + LLC [30] 44.63% SIFT + LDC + LLC [30] 48.45% We also tested the proposed framework with IFV and compared performance with LLC intuitively. From results, we can see SIFT + IFV shows 2% higher accuracy than SIFT + LLC.…”

Section: Methods Accuracymentioning

confidence: 99%

“…We followed the experimental protocol proposed by Chen et al and performed 3-fold cross-validation for the experiments, only using the 12 images from two instances for training and the other 6 images from the third for testing [27]. We repeated this procedure three times, with a different instance serving as the test set and averaged the results.…”

Section: Experiments On Pfid Databasementioning

confidence: 99%

See 1 more Smart Citation

Food Image Recognition via Superpixel Based Low-Level and Mid-Level Distance Coding for Smart Home Applications

2017

View full text Add to dashboard Cite

Abstract:Food image recognition is a key enabler for many smart home applications such as smart kitchen and smart personal nutrition log. In order to improve living experience and life quality, smart home systems collect valuable insights of users' preferences, nutrition intake and health conditions via accurate and robust food image recognition. In addition, efficiency is also a major concern since many smart home applications are deployed on mobile devices where high-end GPUs are not available. In this paper, we investigate compact and efficient food image recognition methods, namely low-level and mid-level approaches. Considering the real application scenario where only limited and noisy data are available, we first proposed a superpixel based Linear Distance Coding (LDC) framework where distinctive low-level food image features are extracted to improve performance. On a challenging small food image dataset where only 12 training images are available per category, our framework has shown superior performance in both accuracy and robustness. In addition, to better model deformable food part distribution, we extend LDC's feature-to-class distance idea and propose a mid-level superpixel food parts-to-class distance mining framework. The proposed framework show superior performance on a benchmark food image datasets compared to other low-level and mid-level approaches in the literature.

show abstract

“…One of the best known works based on local features was presented in [9]. The authors combined three algorithms.…”

Section: Vision-based Techniques For Food Recognitionmentioning

confidence: 99%

Machine Vision in Food Recognition: Attempts to Enhance CBVIR Tools

Sluzek

2016

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

Abstract-Visual identification of complex images (e.g. images of food) remains a challenging problem. In particular, contentbased visual information retrieval (CBVIR) methods, which seem a natural choice for such tasks, are often constrained by specific characteristics of the images of interest and (possibly) other practical requirements. In this paper, a novel CBVIR approach to automatic food identification is proposed, taking into account characteristics of solutions currently existing in this area. Based on limitations of those solutions, we present a scheme in which a co-occurrence of MSER features extracted from three color channels is employed to build a bag-of-words histogram. Subsequently, food images are matched by detecting similarities between those histograms. Preliminary tests on a recently published benchmark dataset UNICT-FD889 reveal certain advantages of the scheme and highlight its limitations. In particular, a need of a novel methodology for segmentation of food images has been identified.

show abstract

PFID: Pittsburgh fast-food image dataset

Cited by 214 publications

References 9 publications

Image Similarity Search using a Negative Selection Algorithm

Image Similarity Search using a Negative Selection Algorithm

Food Image Recognition via Superpixel Based Low-Level and Mid-Level Distance Coding for Smart Home Applications

Machine Vision in Food Recognition: Attempts to Enhance CBVIR Tools

Contact Info

Product

Resources

About