SHAPE RECOGNITION IN NOISY IMAGES USING AI ALGORITHMS

Аннотация

This study investigates the application of artificial intelligence (AI) algorithms for robust shape recognition in noisy binary images, addressing challenges in medical imaging (e.g., organ segmentation in MRI scans), industrial inspection (e.g., defect detection in automotive parts), and remote sensing (e.g., object identification in satellite imagery). Three AI-based methods—Hough Transform (HT), Fourier Descriptors (FD), and Zernike Moments (ZM)— were implemented and evaluated using Python-based tools (OpenCV, Mahotas). Experimental results demonstrate that Zernike Moments achieve the highest accuracy (95%) in high-noise conditions, Fourier Descriptors excel in reconstructing complex contours, and Hough Transform is fastest for detecting basic geometric shapes. A hybrid approach integrating these methods with deep learning, such as Convolutional Neural Networks (CNNs), is proposed to enhance accuracy and scalability. Keywords: Shape Recognition, Noisy Images, Hough Transform, Fourier Descriptors, Zernike Moments,Image Processing, Python, Pattern Recognition, ConvolutionalNeural Networks. 1.Introduction Shape recognition is a cornerstone of computer vision, enabling applications such as organ segmentation inmedical imaging, defect detection inindustrial manufacturing, and object identification in autonomous navigation. Real-world images are often corrupted by noise, such as Gaussian noise in MRI scans or speckle noise in satellite imagery, which distorts object boundaries and challenges traditional geometric methods. AI-based techniques leverage invariant properties to achieve robust shape recognition despite noise, rotation, and scale variations. This study evaluates three AI-based shape recognition methods—Hough Transform (HT), Fourier Descriptors (FD), and Zernike Moments (ZM)—in noisy binary image environments. The methods were tested on a synthetic dataset simulating real-world distortions, with the goal of identifying their strengths and proposing a hybrid framework combining classical descriptors withdeep learning forenhanced performance. 2.Literature Review Gonzalez and Woods (2018) provided foundational techniques for spatial and frequency domain image preprocessing, critical for noise handling. Ballard (1981) extended the Hough Transform to detect arbitrary shapes, improving object detection capabilities. Khotanzad and Hong (1990) introduced Zernike Moments for invariant shape recognition using orthogonal polynomials. Teague (1980) developed moment-based descriptors via general moment theory, enabling complex shape representation. Recent advancements include hybrid models integrating classical descriptors with deep learning. Sonka et al. (2014) emphasized combining spatial and frequency domain analyses for robustness in noisy environments. Dosovitskiy et al. (2021) introduced Vision Transformers (ViT), which outperform traditional CNNs in certain tasks. Liu et al. (2022) proposed page1867 INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE ISSN:2692-5206,ImpactFactor:12,23 AmericanAcademicpublishers,volume05,issue05,2025 Journal: https://www.academicpublishers.org/journals/index.php/ijai EfficientNetV2, a lightweight CNN architecture balancing accuracy and efficiency. These developments highlight thepotential ofhybrid approaches for robust shaperecognition. 3.Methodology 3.1Dataset andExperimental Setup A synthetic dataset of 10 binary images was generated, comprising 3 circles, 3 squares, 2 stars, and 2 triangles to represent diverse shape complexities. Each image was corrupted with Gaussian noise, defined bytheprobability density function: 2 2 1 x−μ + y−μ 2 Thepnoxi,sye le=vels we 2 reexchpos−en to reflect v2ariances in, MμRI=sc0a,nsσ ∈ [0.01,0.1] and satellite imagery 2πσ Other n 2 o σ ise types (e.g., salt-and-pep2per) were not included butare planned for f2uturework. (σ ≈ 0.01− 0.05) Python 3.11(σwas≈u0se.0d5w−ith0t.h1e)following libraries: OpenCV(cv2) for edge detection and contour analysis. NumPyfor numerical computations. Mahotas for Zernike Moments extraction. Matplotlibfor visualization. Experiments were conducted on a Windows machine with 16 GB RAM and an Intel Core i7processor. 3.2ShapeRecognition Techniques 3.2.1HoughTransform (HT) The Hough Transform identifies geometric shapes (e.g., lines, circles) in edge-detected images usinga votingmechanism in parameterspace.For lines, thepolar form is: where is theperpendicular distance from the origin, and is the angle of the line. For circles, theequation is: ρ = xcosθ+ysinθ ρ θ ∈ [0,π] where is thecircle center, and is the2radius. The2 imp2lementationis: edges = cv2.Canny(image, 50,x1−50a) + y−b = r linae,sb=cv2.HoughLines(edges,r1,np.pi/ 180,100) HT is robust topartial occlusion and excels with simpleshapes. 3.2.2FourierDescriptors (FD) Fourier Descriptors represent a shape’s boundary using the Discrete Fourier Transform (DFT). For acontour withpoints ,the complex representation is: TheDFT coefficients are: x t ,y(t) z t = x t +jy t , t = 0