Multi-object face recognition using Content Based Image Retrieval (CBIR)

Fachrurrozi, Muhammad; Erwin, Erwin; Saparudin,; Mardiana, Mardiana

doi:10.1109/icecos.2017.8167132

Cited by 16 publications

(12 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The level of accuracy of face recognition in realtime is smaller than facial recognition in non real time. On the introduction in on realtime with the same data and methods obtained an accuracy of 65.32% [4].…”

Section: Implementation and Resultsmentioning

confidence: 83%

See 1 more Smart Citation

Real-time Multi-object Face Recognition Using Content Based Image Retrieval (CBIR)

Fachrurrozi¹,

Saparudin²,

Erwin³

et al. 2018

IJECE

Self Cite

View full text Add to dashboard Cite

<p>Face recognition system in real time is divided into three processes, namely feature extraction, clustering, detection, and recognition. Each of these stages uses different methods, Local Binary Pattern (LBP), Agglomerative Hierarchical Clustering (AHC) and Euclidean Distance. Multi-face image search using Content Based Image Retrieval (CBIR) method. CBIR performs image search by image feature itself. Based on real time trial results, the accuracy value obtained is 61.64%. </p><p class="Abstract"> </p>

show abstract

Section: Implementation and Resultsmentioning

confidence: 83%

“…Content Based Image Retrieval has several processes to get good results, one of the process is by feature extraction to get the value of each facial feature [4]. The Local Binary Pattern algorithm is capable of characterizing and distinguishing surface textures.…”

Section: Introductionmentioning

confidence: 99%

Real-time Multi-object Face Recognition Using Content Based Image Retrieval (CBIR)

Fachrurrozi¹,

Saparudin²,

Erwin³

et al. 2018

IJECE

Self Cite

View full text Add to dashboard Cite

show abstract

“…The first step in this research before images are trained and tested, the image must be shared from an RGB image to a binary image. In this pre-approval picture as agreed in figure1, using OpenCV in pythonand results of Binary Images are performed on low variant texture images to produce high-quality images [11].…”

Section: A Preprocessingmentioning

confidence: 99%

Arabic Handwritten Digit Recognition using Convolutional Neural Network

Pardamean*,

Yuliana,

Watmah

et al. 2020

IJRTE

View full text Add to dashboard Cite

Arabic is the most widely used language in the world, especially the Arab League Country. Of course, in those countries often use Arabic numeral in banks and business applications, postal zip code and data entry application. This research has focused on handwriting recognition of Arabic numeral that has unlimited variation in human handwriting such as style and shape. The proposed method on the deep learning technique is Convolutional Neural Network. LeNet-5 architect also used in training and recognizing the handwritten image of Arabic numeral as much as 70000 images derived from MADbase dataset. The experimental result on 10000 images of database used is by comparing the number of epoch in training process yields, and the average accuracy is 97.67%.

show abstract

“…CBIR, a picture seeking systems in light of picture highlight, is executed as the looking technique. Based experiments and the testing result, recall and precision values are 65.32% and 64.93% respectively [11]…”

mentioning

confidence: 94%

Improved Approaches Edge Direction Histogram and HSV Histogram, Color Auto Correlagram; Gabor Wavelet Transforms using CBIR

Sharma¹,

Kushwah²

2018

IJCA

View full text Add to dashboard Cite

Content Based Image Retrieval (CBIR) is a creating pattern in Digital Image Processing (DIP) for seeking and recovering the question picture from extensive variety of databases. CBIR framework comprise of different stages to concentrate and match the highlights and hunt the pictures from the substantial scale picture databases based on visual substance such as Color, Shape and Texture according to the user's interest. To supply the reasonable answer to the client query, CBIR provides some run of work. A new method is planned in this paper for color picture indexing by developing the ease of SVM system. A New technique is proposed on this paper for coloration photograph indexing via exploiting the simplicity of the Histogram equalization method. In this algorithm, now we have proposed a mixture of color, shape and texture features. In this approach, the past work is improved to accomplish better precision. In this paper we propose histogram equalization to improve image quality and applied distance matrix to get better result than base work.At that point we encrypt the three channels independently. Here component Extraction was viewed as the paired order issue and SVM was utilized for arrangement this issue and the procedure of grouping is given to the whole picture which are extricated after the feature extraction process.

show abstract

Multi-object face recognition using Content Based Image Retrieval (CBIR)

Cited by 16 publications

References 6 publications

Real-time Multi-object Face Recognition Using Content Based Image Retrieval (CBIR)

Real-time Multi-object Face Recognition Using Content Based Image Retrieval (CBIR)

Arabic Handwritten Digit Recognition using Convolutional Neural Network

Improved Approaches Edge Direction Histogram and HSV Histogram, Color Auto Correlagram; Gabor Wavelet Transforms using CBIR

Contact Info

Product

Resources

About