Return of the king: The Fourier transform based descriptor for visual object classification

Çevikalp, Hakan; Kurt, Zühal; Onarcan, Ahmet Okan

doi:10.1109/siu.2013.6531160

Cited by 4 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…• SBFD raises another novelty of this work in terms of applying a novel feature extractor tool for wheat cultivar classification. The SBFD is an improved version of Fourier Descriptors [22], which is employed for object classification. Similar to work of [33], we have extracted Fourier Descriptors on contour fragments to be forwarded into the classifier.…”

Section: Feature Extraction Toolsmentioning

confidence: 99%

“…For this purpose, we have developed two frameworks: (i) using traditional BoW features and (ii) executing celebrated CNN features, respectively. Since using a single feature extraction algorithm with a predetermined classifier does not promise reasonable performance for the wheat representation, we have employed BoW [18] features on like scale invariant feature transform (SIFT) [19], speeded-up robust features (SURF) [20], dense-scale invariant feature transform (DSIFT) [18], LBP [21] and shape-based Fourier descriptor (SBFD) [22] for decision-making with consensus rule on SVM, ANN and KNN classifiers. Going through the literature on machine learning systems for wheat identification, one can observe that the single model [7,23] has been usually employed in the case of identification process.…”

Section: Motivationmentioning

confidence: 99%

See 1 more Smart Citation

Consensus rule for wheat cultivar classification on VL, VNIR and SWIR imaging

Işık

Özkan

Demirez

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

To facilitate the quality assessment of wheat cultivars, diverse imaging tools and techniques have been applied in order to omit the expert decision, which can cause failure in the identification of the wheat cultivar's label and its quality simultaneously. To minimize the risks caused by the expert's decision, a promising framework for identification is greatly required to more effectively assess wheat type. Therefore, to be beneficial to this association, two methods have been developed by performing traditional and modern feature extraction algorithms on visible light (VL), visible near-infrared (VNIR) and short-wave infrared (SWIR) imaging as well as a fusion of these imaging systems. The proposed systems are called the bag of word (BoW) framework and convolutional neural networks (CNN) framework. With regard to wheat cultivar detection, the consensus rule has been established based on decisions predicted by CNN and BoW frameworks. The accuracy results obtained by consensus rule indicate that we have achieved 99.94% and 68.94% in case of CNN framework and BoW framework, respectively. Experimental results suggest that BoW features are not suitable to represent and match texture patterns such as repeated wheat kernels in an image, whereas CNN features always outperform handcrafted elements and properties for all datasets.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Section: Feature Extraction Toolsmentioning

confidence: 99%

Section: Motivationmentioning

confidence: 99%

Consensus rule for wheat cultivar classification on VL, VNIR and SWIR imaging

Işık

Özkan

Demirez

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Bir sonraki aşamada imgeler, "bag of words" modeli [3,4,5] ile betimlenmiştir. "Bag of words" modeli, her bir imgeyi sıralı temsili yamaların birleşimi olarak derlemektedir.…”

Section: Yöntemunclassified

“…Ayrıca imgelerde arka plan son derece karmaşıktır ve bazı imgelerde nesne sınıfına ait örnek görüntüler başka nesneler tarafından kapatılmıştır. Bu sebeple imgeleri betimlemek için daha önce belirtilen "bag of words" modeli [3,4,5] kullanılmıştır. Seçilen etiketsiz sorgu imgesiyle etiketli imgelerin öznitelikleri "Chi-Squared" uzaklığı kullanılarak karşılaştırılmış, ardından sorgu imgesi ile etiketli imge histogramları arasındaki uzaklığı minimum olan 250 öznitelik vektörü belirlenir.…”

Section: Deneysel çAlişmalarunclassified

Semi automatic annotation tool

Dongel

Çevikalp

2014

2014 22nd Signal Processing and Communications Applications Conference (SIU)

View full text Add to dashboard Cite

ÖZETÇEİmge erişiminde kullanılan etiketli imgelerin etiketleme işlemi, tam-otomatik algoritmalar tarafından yapıldığında imge etiketleri genellikle hatalar ve eksik etiketler içermektedir. Bu etiketleri temizleme ve düzeltme işi genellikle manuel olarak kişiler tarafından yapılır. Farklı kişiler tarafından yapılan etiketleme işlemi de bu kişiler arasında koordinasyonu gerekli kılmaktadır. Bu bildiride, imge etiketleme için Matlab GUI ile tasarlanan yarı otomatik bir imge etiketleme aracı önerilmiştir. Önerilen bu çalışmada, ilk olarak verilen sorgu imgesinin ve etiketli imgelerin öznitelikleri karşılaştırılarak öznitelikler arasında "Chi-Squared" uzaklık ölçütü kullanılarak en kısa mesafe olanlar belirlenir. Daha sonra kullanılan uzaklık ölçütü göz önünde bulundurularak sorgu imgesine en çok benzeyen imgelerin etiket bilgileri kullanılarak, sorgu imgesinin etiketlenmesinde kullanılabilecek etiketlerden önem sırasına göre dizilmiş sıralı bir liste oluşturulur. Kullanıcı da oluşturulan bu etiket listesinden sorgu imgesiyle alakalı etiketleri seçerek etiketleme işlemini tamamlar. Listeyle döndürülen etiketlerin yeterli olmaması durumunda, geliştirdiğimiz araç aynı zamanda kullanıcıya liste dışında kendi etiketlerini de girmesine olanak vermektedir. Bu sayede önerilen yöntem ile hem zaman kaybı hem de insan algısının öznelliği en aza indirgenerek sistematik ve tutarlı etiketleme gerçekleştirilmiş olur. ABSTRACTWhen image labeling (annotation) process for image retrieval is performed by fully automatic algorithms, labels have noise, errors and missing labels. Correcting labels gathered automatically from web (using information around an image such as text, user-tags, etc.) is done manually using human labor. Therefore, coordination of different indivuduals is necessary for a consistent annotation. In this paper, a semiautomatic annotation tool designed with Matlab GUI has been proposed for an efficient and consistent image labeling. In the proposed framework, we first compare visual features of the query image and the labeled gallery images by using "Chi-Squared" distance. Then we create an ordered label list by using the labels of the closest images. The user finally selects the appropriate labels from the list and finishes the labeling process. The tool also allows one to enter new labels in case the returned labels are not enough to describe the image content. In this way the subjectivity of human perception and loss of time are reduced as well as consistency and coordination among different indivuduals' annotations are accomplished.

show abstract

“…In this paper, we concentrate on the descriptors, which are used for describing image patches and we introduce a new descriptor using weighted histograms of phase angles of Fourier Transform to be used in BoW or FV models for visual object classification. A preliminary version of this paper has appeared in [21]. This paper extends our previous work with (1) a more elaborated analysis of the current related work on image representation, (2) a more detailed description of the proposed descriptor and modifications on the descriptor by changing the histogram construction, (3) more experiments on larger image classification data sets, and (4) testing different design methodologies such as the sizes of cells, the sizes of the phase angle bins, and different normalizations of histograms on the classification performance.…”

Section: Introductionmentioning

confidence: 99%

The Fourier Transform Based Descriptor for Visual Object Classification

Çevikalp¹,

Kurt²

2017

ANADOLU UNIVERSITY JOURNAL OF SCIENCE AND TECHNOLOGY a - Applied Sciences and Engineering

View full text Add to dashboard Cite

Image representation models such as bag of words (BoW) or Fisher vector (FV), which are built depending on encoding local features, are commonly used in visual object classification tasks. In this context, the local patches sampled from images are represented by different texture and shape descriptors such as Scale Invariant Feature Transform (SIFT), Local Binary Pattern (LBP), Speed up Robust Features (SURF), etc. In this study, we propose a new descriptor using weighted histograms of phase angles of local 2-D discrete Fourier transform (FT). We make comparisons with the classification accuracies achieved by using the proposed descriptor to the ones achieved by other commonly used descriptors on Caltech-101, Coil-100 and PASCAL VOC 2007 databases. Experimental results show that our proposed descriptor yields good classification accuracies (the best results on Coil-100, and the second best result on Caltech-101 and PASCAL VOC 2007 datasets) indicating that FT based local descriptors obtain important properties of images that are valuable for visual object classification. By combining image representations resulting from FT descriptor with the representations resulting from other descriptors, accuracies even get better demonstrating that tested descriptors encode different supplementary knowledge.

show abstract

Return of the king: The Fourier transform based descriptor for visual object classification

Cited by 4 publications

References 17 publications

Consensus rule for wheat cultivar classification on VL, VNIR and SWIR imaging

Consensus rule for wheat cultivar classification on VL, VNIR and SWIR imaging

Semi automatic annotation tool

The Fourier Transform Based Descriptor for Visual Object Classification

Contact Info

Product

Resources

About