As one of the important parts of face recognition, face image segmentation has become a major focus of human feature recognition. In this paper, the AdaBoost algorithm and Gabor texture analysis algorithm are used to segment an image containing multiple faces, which effectively reduces the false detection rate in face image segmentation. In face image segmentation, the image containing face data is first analyzed by texture using the Gabor algorithm, and different thresholds are set for different skin-like areas, thereby removing skin-like areas in the background image. Then, the face areas are detected using the AdaBoost algorithm, and the detected face areas are segmented. Experiments have shown that the proposed method can quickly and accurately segment faces in the image, and effectively reduce the loss and false detection rates.
| Mualliflar | Mamatov, N.S., Niyozmatova, N.A., Tojiboyeva, Sh.X., Mashanpin, T.V., Yaxyaev, B.Yu. |
|---|---|
| Jurnal | Рақамли технологияларнинг назарий ва амалий масалалари |
| Nashr sanasi | 2025-04-06 |
| Jild | 8 |
| Son | 1 |
| Betlar | 183-189 |
| Til | Rus |
| DOI | 10.62132/ijdt.v8i1.250 |
DOI: 10.62132/ijdt.v8i1.250 · Maqolaning asl sahifasi
yuz tasviri, Gabor filtri, AdaBoost, face image, Gabor filter, AdaBoost
This paper analyzes two approaches to the prediction of cardiovascular diseases, which have a binary classification problem based on the same Cleveland benchmark and aim to identify the advantages of quantum computing…
This paper provides a comprehensive overview of optimal methods and processes for recording, processing, and classifying electromyography (EMG) signals in the context of human movement rehabilitation. It begins by…
This article presents a mathematical model and numerical algorithms for solving a three-dimensional fluid filtration problem in a porous medium, using the hydrodynamic process of in-situ leaching (ISL) as an example…
This study analyzes the efficiency of SHA (Secure Hash Algorithm) family algorithms depending on message length. The execution time of hashing processes for SHA-1 and SHA-2 (SHA-224, SHA-256, SHA-384, SHA-512)…
This research work is devoted to the problem of classifying diseases in kidney computed tomography images using neural networks. The novelty and uniqueness of the research is that it studies not only the traditional…
The article is devoted to the development of an information model of vocational guidance, focused on the analysis of competencies using the k-nearest neighbors (k-NN) method. In this work, the method is used to assess…
This paper presents an improved mathematical model for describing filtration processes in two-layer dynamically interconnected oil reservoirs, incorporating the dependence of hydrodynamic parameters on changes in…
The article considers the problem of forecasting changes in groundwater levels using numerical methods based on a three-dimensional nonlinear mathematical model. The model takes into account factors affecting the…
Clustering is one of the main tasks of data analysis aimed at grouping objects into homogeneous subsets without predetermined labels. This article examines the method of column clustering. It uses the concept of…
Natural Language Processing (NLP) has witnessed remarkable advancements in recent years, driven by the development of sophisticated algorithms and models such as GPT-4, T5, and BERT. These models have revolutionized the…
Рақамли технологияларнинг назарий ва амалий масалалари — barcha maqolalar