Improving the Performance of CBIR on Islamic Women Apparels Using Normalized PHOG

Mutia, Cut; Arnia, Fitri; Muharar, Rusdha

doi:10.11591/eei.v6i3.657

Cited by 11 publications

(9 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The research on shape-based image retrieval carried out by [6] compared several methods, such as HOG, pyramid HOG (PHOG), and normalized PHOG (NPHOG). The first step was to detect an object's face using the Viola-Jones method, with the center point of the face chosen as the reference for normalization.…”

Section: Feature Extraction Based On Traditional Methodsmentioning

confidence: 99%

“…The authors recommended the combination of color and texture features in future research to improve retrieval performance. Mutia et al [6] stated that precision is higher for color features than the texture in the image extraction process and lowest in the striped fabric category, where embedded lines cause image similarity.…”

Section: Feature Extraction Based On Traditional Methodsmentioning

confidence: 99%

“…A combination of techniques that can handle texture and color features is needed to improve accuracy for image types with complex textures. [7], [8], [10], [11], [13], [15], [19] Small feature dimensions [8], [15], [16], [21] Faster computation time [8], [9], [12], [15] Can handle background interference and scene rotation [14], [53] Not suitable for complex fabric images [7], [9], [11] Use of a single feature has low retrieval accuracy [6], [8], [11], [12], [17], [18], [28]. Retrieval accuracy is lower than with CNNs…”

Section: Comparison Of Traditional and Cnn Feature Extrationmentioning

confidence: 99%

See 2 more Smart Citations

Content-based image retrieval for fabric images: A survey

Tena

Hartanto

Ardiyanto

2021

IJEECS

View full text Add to dashboard Cite

In <span>recent years, a great deal of research has been conducted in the area of fabric image retrieval, especially the identification and classification of visual features. One of the challenges associated with the domain of content-based image retrieval (CBIR) is the semantic gap between low-level visual features and high-level human perceptions. Generally, CBIR includes two main components, namely feature extraction and similarity measurement. Therefore, this research aims to determine the content-based image retrieval for fabric using feature extraction techniques grouped into traditional methods and convolutional neural networks (CNN). Traditional descriptors deal with low-level features, while CNN addresses the high-level, called semantic features. Traditional descriptors have the advantage of shorter computation time and reduced system requirements. Meanwhile, CNN descriptors, which handle high-level features tailored to human perceptions, deal with large amounts of data and require a great deal of computation time. In general, the features of a CNN's fully connected layers are used for matching query and database images. In several studies, the extracted features of the CNN's convolutional layer were used for image retrieval. At the end of the CNN layer, hash codes are added to reduce </span>search time.

show abstract

Section: Feature Extraction Based On Traditional Methodsmentioning

confidence: 99%

Section: Feature Extraction Based On Traditional Methodsmentioning

confidence: 99%

Section: Comparison Of Traditional and Cnn Feature Extrationmentioning

confidence: 99%

See 1 more Smart Citation

Content-based image retrieval for fabric images: A survey

Tena

Hartanto

Ardiyanto

2021

IJEECS

View full text Add to dashboard Cite

show abstract

“…CBIR bertujuan untuk menemukan cintra busana muslimah berdasarkan isi citra. Beberapa tahun belakang, busana muslimah merupakan objek penelitian yang sering digunakan pada CBIR [1]- [4]. Penelitian ini, menggunakan Deskriptor Warna Dominan (DWD) dan Deskriptor Korelogram Warna Dominan (DKWD) untuk ekstraksi fitur warna.…”

Section: Pendahuluanunclassified

Content Based Image Retrieval Busana Muslimah Menggunakan Fitur Kombinasi PHOG dan DCD

Mutia

Akmal

2021

JurTI

Self Cite

View full text Add to dashboard Cite

- The development of Muslim clothing has increased significantly, especially in Indonesia, where the majority of the population is Muslim. Designers have appeared with a variety of fashion styles that attract consumers, especially young consumers. Technological developments have also influenced the way designers promote and sell their work by utilizing online commerce. So that consumers can search and find various models and colors of clothing that interest them. In this study, the search for Muslim clothing was carried out using the visual content of images or also known as features. The features used in this study are a combination of color and shape features, because shape and color are an attraction for consumers in choosing clothes. Search using image content as a query is known as CBIR. This study applies the PHOG as a shape feature extraction method and the DCD for the extraction of color features. The dataset used is 180 images of Muslim clothing. The performance of CBIR Muslim clothing using a combination of PHOG and DCD features is measured with recall, precision, and f-measure parameters. The results of the performance measurement show that the combination of PHOG and DCD features is better applied to blouse pants clothing. The highest scores were obtained from the red clothing group of 68% (P), 22.2%, and 33.3% (F). Then followed by a group of robes, and outerwear. Keywords - CBIR, PHOG, DCD, Feature and Clothing. Abstrak - Busana muslimah memiliki bentuk dan warna yang beragam dan menarik minat konsumen, banyak situs belanja online yang mempromosikan dan menjual produknya. Namun, pencarian busana muslimah pada situs tersebut masih menggunakan teks, sehingga hasil pencarian produknya sering tidak sesuai dengan harapan konsumen.Pada penelitian ini, pencarian busana muslimah dilakukan dengan menggunakan isi visual citra atau disebut juga sebagai fitur, adapun fitur yang digunakan adalah kombinasi fitur warna dan bentuk, karena bentuk (model) dan warna merupakakan daya tarik bagi konsumen dalam memilih busana. Pencarian menggunakan isi gambar sebagai query dikenal dengan Content Based Image Retrieval (CBIR). Penelitian ini menerapkan Pyramid Histogram of Oriented Gradient (PHOG) sebagai metode ekstraksi fitur bentuk dan Dominant Color Descriptor (DCD) untuk ekstraksi fitur warna. Dataset yang digunakan ada 180 citra busana muslimah, terdiri dari 60 citra blus celana, 60 gamis, dan 60 outerwear. Kemiripan query dengan dataset dilakukan dengan menghitung jarak Euclidean. Pengukuran Kinerja CBIR busana muslimah menggunakan kombinasi fitur PHOG dan DCD dilakukan dengan menghitung nilai recall, precision, dan f-measure. Hasil pengukuran kinerja menunjukkan bahwa kombinasi fitur PHOG dan DCD lebih baik diterapkan pada busana blus-celana. Berdasarkan pengukuruan kinerja dengan precision (P), recall (R0, dan f-measure (F). Nilai tertinggi diperoleh dari kelompok busana berwarna merah sebesar 68 % (P), 22.2%, dan 33.3 % (F). Kemudian diikuti dengan kelompok busana gamis, dan outerwear. Kata Kunci - CBIR, PHOG, DCD, Fitur dan Busana.

show abstract

“…Using gradient vector flow snake (GVFS) method and the CBIR technique in implementing an application [6]. Not only that, the CBIR has been applied using the pyramid histogram of oriented gradients (PHOG) approach in extracting shape [7]. The research presented in this area is focused to reduce the semantic gap between the image feature representation and human visual understanding.…”

Section: Introductionmentioning

confidence: 99%

Application of content based image retrieval in digital image search system

2021

View full text Add to dashboard Cite

Multimedia data is growing rapidly in the current digital era, one of which is digital image data. The increasing need for a large number of digital image datasets makes the constraints faced eventually drain a lot of time and cause the process of image description to be inconsistent. Therefore, a method is needed in processing the data, especially in searching digital image data in large image dataset to find image data that are relevant to the query image. One of the proposed methods for searching information based on image content is content based image retrieval (CBIR). The main advantage of the CBIR method is automatic retrieval process, compared to traditional keyword. This research was conducted on a combination of the HSV color histogram methods and the discrete wavelet transform to extract color features and textures features, while the chi-square distance technique was used to compare the test images with images into a database. The results have showed that the digital image search system with color and texture features have a precision value of 37.5% - 100%, with an average precision value of 80.71%, while the percentage accuracy is 93.7% - 100% with an average accuracy is 98.03%.

show abstract

Improving the Performance of CBIR on Islamic Women Apparels Using Normalized PHOG

Cited by 11 publications

References 5 publications

Content-based image retrieval for fabric images: A survey

Content-based image retrieval for fabric images: A survey

Content Based Image Retrieval Busana Muslimah Menggunakan Fitur Kombinasi PHOG dan DCD

Application of content based image retrieval in digital image search system

Contact Info

Product

Resources

About