scholarly journals Aplikasi Pengenalan Batu Akik Berbasis Android

2018 ◽  
pp. 10
Author(s):  
Yogiswara Dharma Putra ◽  
I Ketut Gede Darma Putra ◽  
I Putu Agus Eka Pratama
Keyword(s):  
Image Retrieval ◽  
Euclidean Distance ◽  
Gabor Filter

Batu akik merupakan sebuah mineral alamiah dari prosedur geologi yang memiliki komponen kimiawi. Pemakaian perhiasan yang menggunakan batu akik popular di kalangan masyarakat umum karena keindahan dan keunikannya yang juga menjadi salah satu daya tarik bagi peminat batu akik. Penelitian Aplikasi Pengenalan Batu Akik Berbasis Android merupakan sistem image retrieval berbasis Android yang dirancang mampu memberikan kemudahan bagi peminat batu akik untuk mencari informasi dengan cepat mengenai batu akik, salah satunya adalah untuk mencari jenis-jenis batu akik. Pencarian jenis-jenis batu akik pada aplikasi dilakukan dengan Metode HSV dan YCbCr menggunakan histogram warna untuk mengenali warna, Gabor Filter untuk mengenali tekstur dan perhitungan Euclidean Distance untuk mencari kecocokan dari citra query dengan citra database. Uji coba dan analisa pada fitur warna HSV dan YCbCr menghasilkan akurasi sebesar 60,4% dan 59,6%, sedangkan Fitur tekstur Filter Gabor mendapatkan hasil akurasi pada theta 0 derajat sebesar 46,8%, theta 45 derajat sebesar 45,6%, theta 90 derajat sebesar 45.2% dan theta 135 derajat sebesar 42,8%. Kombinasi deteksi Metode HSV menggunakan histogram warna dan Filter Gabor mendapatkan akurasi lebih baik yaitu sebesar 60% dibandingkan Metode YCbCr menggunakan histogram warna dan Filter Gabor dengan hasil akurasi sebesar 56%.

scholarly journals Studi Akurasi Karakteristik Retina sebagai Future Identification dengan Euclidean Distance Metrics

2021 ◽  
Vol 16 (1) ◽  
pp. 19
Author(s):  
Suhendro Yusuf Irianto ◽  
Ribut Yulianto ◽  
Sri Karnila ◽  
Dona Yuliawati
Keyword(s):  
Image Retrieval ◽  
Euclidean Distance ◽  
Distance Metrics

Penelitian ini menghasilkan sistem keamanan menggunakan biometrik, dengan menggunakan retina sebagai identitas pengenalan yang akurat, serta efektif untuk meningkatkan proses identifikasi pada retina dimasa depan (future identification). Hal ini sangat penting untuk menentukan keakuratan sifat biometrik apa yang paling baik di dalam proses mengidentifikasi di masa depan, sekaligus membangun suatu sistem aplikasi atau tools yang dapat digunakan untuk mengetahui karakteristik distance meterics untuk mengukur akurasi retina sebagai identitas dimasa depan (future identification). Penggunaan retina dapat menjadi salah satu alternatif identifikasi manusia  seperti  untuk  pengganti  PIN  ATM  Bank,  Paspor  dan bidang-bidang lain yang memerlukan tingkat keamanan tinggi atau mustahil untuk dapat dipalsukan. Hasil dari penelitian ini ialah berbentuk pengujian untuk membuktikan tingkat akurasi CBIR dengan menggunakan citra query dengan dibangun database sebanyak 5.000 citra retina. Metode yang akan digunakan dalam menentukan similarity dan identification dengan menggunakan fitur warna. Histogram warna untuk pencarian citra dikerjakan dengan mengitung jumlah koefisien DCT dari setiap warna. Hasil penelitian menunjukan bahwa akurasi algoritma mendekati nilai 90%, akurasi ini cukup bagus di bidang image retrieval.  Di lihat dari kecepatan proses retrieval juga cukup cepat dimana rata –rata kecepatan proses dengan menggunakan 2.000 citra digital adalah kurang dari 10 detik.

Image Retrieval of Self-Adapt Distance Measure Based on SLLE

2014 ◽  
Vol 989-994 ◽  
pp. 3675-3678
Author(s):  
Xiao Fen Wang ◽  
Hai Na Zhang ◽  
Xiu Rong Qiu ◽  
Jiang Ping Song ◽  
Ke Xin Zhang
Keyword(s):  
Image Retrieval ◽  
High Dimension ◽  
Topological Structure ◽  
Euclidean Distance ◽  
Distance Measure ◽  
Content Based Image Retrieval ◽  
Locally Linear Embedding ◽  
Euclidean Distance Measure ◽  
Linear Embedding ◽  
Dimension Space

Self-adapt distance measure supervised locally linear embedding solves the problem that Euclidean distance measure can not apart from samples in content-based image retrieval. This method uses discriminative distance measure to construct k-NN and effectively keeps its topological structure in high dimension space, meanwhile it broadens interval of samples and strengthens the ability of classifying. Experiment results show the ADM-SLLE date-reducing-dimension method speeds up the image retrieval and acquires high accurate rate in retrieval.

Fuzzy Relevance Feedback in Image Retrieval for Color Feature Using Query Vector Modification Method

2010 ◽  
Vol 14 (1) ◽  
pp. 34-38 ◽  
Author(s):  
M. Rahmat Widyanto ◽  
◽  
Tatik Maftukhah ◽  
Keyword(s):  
Image Retrieval ◽  
Relevance Feedback ◽  
Euclidean Distance ◽  
Retrieval System ◽  
User Feedback ◽  
Image Similarity ◽  
Modification Method ◽  
Image Retrieval System ◽  
Membership Value ◽  
Image Computation

Fuzzy relevance feedback using Query Vector Modification (QVM) method in image retrieval is proposed. For feedback, the proposed six relevance levels are: “very relevant”, “relevant”, “few relevant”, “vague”, “not relevant”, and “very non relevant”. For computation of user feedback result, QVM method is proposed. The QVM method repeatedly reformulates the query vector through user feedback. The system derives the image similarity by computing the Euclidean distance, and computation of color parameter value by Red, Green, and Blue (RGB) color model. Five steps for fuzzy relevance feedback are: image similarity, output image, computation of membership value, feedback computation, and feedback result. Experiments used QVM method for six relevance levels. Fuzzy relevance feedback using QVM method gives higher precision value than conventional relevance feedback method. Experimental results show that the precision value improved by 28.56% and recall value improved 3.2% of conventional relevance feedback. That indicated performance Image Retrieval System can be improved by fuzzy relevance feedback using QVM method.

The Technique of Shape-Based Multi-Feature Combination of TradeMark Image Retrieval

2012 ◽  
Vol 429 ◽  
pp. 287-291 ◽  
Author(s):  
Cong Zhang ◽  
Fu Cheng You
Keyword(s):  
Image Retrieval ◽  
Euclidean Distance ◽  
Feature Matching ◽  
Region Growing ◽  
Local Information ◽  
Feature Combination ◽  
Single Feature ◽  
Hu Moments ◽  
Global Matching ◽  
Better Than

At present, the technique of trademark image retrieval based on multi-feature combination of the shape mainly includes single-feature global matching or local matching and multi-feature matching, which is playing a more and more important role in the area of the trademark image retrieval. In this paper, due to the deficiency described by some single shape-based features, the technique of the multi-feature combination trademark image retrieval is proposed based on the region and the edge of a shape. Firstly, a trademark image is segmented with region growing, then low order Hu moments and eccentricity are extracted on the resulting region, which is able to express the local information of the image; Secondly, there is an extraction of Compactness and Convexity, which describe the global feature of the image, on the edge extracted with Canny. At last, the combination of the multi-feature is applied to get a Euclidean distance. Good results have been obtained in the following experiment, which proves the multi-feature combination way is better than other single-feature ways.

scholarly journals Deep Feature Learning with Manifold Embedding for Robust Image Retrieval

Algorithms ◽  
2020 ◽  
Vol 13 (12) ◽  
pp. 318
Author(s):  
Xin Chen ◽  
Ying Li
Keyword(s):  
Image Retrieval ◽  
Euclidean Distance ◽  
Large Scale ◽  
Training Image ◽  
Fine Tuning ◽  
Image Feature ◽  
Similarity Measurement ◽  
Local Geometry ◽  
Robust Image ◽  
Image Pairs

Conventionally, the similarity between two images is measured by the easy-calculating Euclidean distance between their corresponding image feature representations for image retrieval. However, this kind of direct similarity measurement ignores the local geometry structure of the intrinsic data manifold, which is not discriminative enough for robust image retrieval. Some works have proposed to tackle this problem by re-ranking with manifold learning. While benefiting better performance, algorithms of this category suffer from non-trivial computational complexity, which is unfavorable for its application to large-scale retrieval tasks. To address the above problems, in this paper, we propose to learn a robust feature embedding with the guidance of manifold relationships. Specifically, the manifold relationship is used to guide the automatic selection of training image pairs. A fine-tuning network with those selected image pairs transfers such manifold relationships into the fine-tuned feature embedding. With the fine-tuned feature embedding, the Euclidean distance can be directly used to measure the pairwise similarity between images, where the manifold structure is implicitly embedded. Thus, we maintain both the efficiency of Euclidean distance-based similarity measurement and the effectiveness of manifold information in the new feature embedding. Extensive experiments on three benchmark datasets demonstrate the robustness of our proposed method, where our approach significantly outperforms the baselines and exceeds or is comparable to the state-of-the-art methods.

Sign in / Sign up

Export Citation Format

Share Document