Adaptive local thresholding based number plate detection

Under maize-soybean rotation systems, weeds and crops at the seedling stage in dryland fields exhibit high similarity in morphological structure, scale distribution, and spatial arrangement. In addition, complex illumination conditions, occlusion, and background interference further complicate accurate weed discrimination. To address these challenges, this study proposes an improved YOLOv11n-based weed detection method for seedling-stage crops under dryland rotation conditions, aiming to enhance detection accuracy and robustness in UAV-acquired field images. Three key improvements were introduced to enhance model performance: (1) the incorporation of Dynamic Convolution (DynamicConv) to adaptively strengthen feature representation for weeds with varying morphologies and scales in low-altitude remote sensing imagery; (2) the design of a SlimNeck lightweight feature fusion architecture to improve multi-scale feature propagation efficiency while reducing computational cost; (3) the cascaded group attention mechanism (CGA) is integrated into the C2PSA module, thereby improving discrimination capability under complex background conditions. These results represent consistent improvements over baseline models, including YOLOv5, YOLOv6, YOLOv8, YOLOv11, and YOLOv12. Specifically, detection performance for broadleaf weeds and Poaceae weeds reached mAP@0.5 values of 87.2% and 73.9%, respectively. Overall, the proposed method demonstrates superior detection accuracy and stability for seedling-stage weed identification under rotation conditions, providing reliable technical support for variable-rate herbicide application and precision field management.

본 논문은 한글 및 영문자의 구조적 특징을 이용하여 자연영상에서 문자영역을 검출하는 기법을 제안하였다. 자연 영상에서 에지 특징 값을 추출하고 추출된 특징 값은 필터링을 수행하여 문자의 특징에 맞지 않는 특징 값을 제거하여 문자영역 후보를 선정한다. 선정된 문자영역 후보는 한글 자소 병합 알고리즘으로 하나의 문자로 병합하여 후보 문자영역으로 검출하고, 한글 문자 유형 판별 알고리즘으로 한글 문자영역 여부를 판별함으로서 한글 문자영역을 검출하고, 영문자는 영문자 에지 특징 값을 적용하여 영문자 영역을 검출한다. 실험결과, 복잡한 배경을 갖고 다양한 환경에서 촬영된 영상에서 한글 및 영문자 영역을 효과적으로 검출하였고, 제안한 문자영역 검출 방법은 향상된 검출 결과를 보여 주었다. We proposes the method to detect the Hangul and English character region from natural image using structural feature of Hangul and English Characters. First, we extract edge features from natural image, Next, if features are not corresponding to the heuristic rule of character features, extracted features filtered out and select candidates of character region. Next, candidates of Hangul character region are merged into one Hangul character using Hangul character merging algorithm. Finally, we detect the final character region by Hangul character class decision algorithm. English character region detected by edge features of English characters. Experimental result, proposed method could detect a character region effectively in images that contains a complex background and various environments. As a result of the performance evaluation, A proposed method showed advanced results about detection of Hangul and English characters region from natural image.

A modular approach on an adaptive thresholding method for segmentation of cell regions in bioelectric images with complex lighting environments and background conditions is presented in this paper. Preprocessing steps involve low-pass filtering of the image and local contrast enhancement. This image is then adaptively thresholded which produces a binary image. The binary image consists of cell regions and the edges of a metal electrode that show up as bright spots. A local region based approach is used to distinguish between cell regions and the metal electrode tip that cause bright spots. Regional properties such as area are used to separate the cell regions from the non-cell regions. Special emphasis is given on the detection of twins and triplet cells with the help of watershed transformation, which might have been lost if form-factor alone were to be used as the geometrical descriptor to sepa rate the cell and the non-cell regions. Keywords: bioelectric images, image segmentation, adaptive thresholding, cell segmentation, local contrast enhancement, watershed transformation, template matching

Detecting text in video or natural scene image is quite challenging due to the complex background, various fonts and illumination conditions. The preprocessing period, which suppresses the nontext areas so as to highlight the text areas, is the basis for further text detection. In this paper, a novel graph-based background suppression method for scene text detection is proposed. Considering each pixel as a node in the graph, our approach incorporates pixel-level and context-level features into a graph. Various factors contribute to the unary and pair wise cost function which is optimized via max-flow/min-cut algorithm [16] to get a binary image whose nontext pixels are suppressed so that text pixels are highlighted. Furthermore, the proposed background suppression method could be easily combined with other detection methods to improve the performance. Experimental results on ICDAR 2011 competition dataset show promising performance.

Accurate and effective water leakage detection in tunnel linings under complex illumination conditions is crucial for ensuring operational safety. This paper proposed a method for detecting water leakage based on infrared vision and an enhanced U-shaped network (UNet) architecture. Initially, the lightweight Azure Kinect sensor was employed to capture both infrared and RGB images of tunnel linings under different illumination conditions. Three datasets: the RGB image under normal illumination (NRGB), the infrared image under normal illumination (NIR), and the infrared image under low illumination (LIR) were created. Subsequently, an enhanced UNet architecture (UKAN) was introduced for water leakage segmentation in tunnel linings. Moreover, Score-weighted and Layer-wise class activation mapping (CAM) were adopted to analyze the model’s decision-making process. Experimental results revealed that the average detection accuracy for the NIR exceeded that of the NRGB by 2.4%, while the LIR was higher by 1.43%. The proposed UKAN architecture achieved optimal mean intersection over union scores of 84.1%, 86.5%, and 85.7% on NRGB, NIR, and LIR. Additionally, visual interpretability analysis showed that the UKAN’s learning process was smooth, gradually shifting its focus from low-level features to target regions. This methodology facilitates efficient and accurate water leakage detection in tunnel linings under varying illumination conditions.

Automatic Number Plate Recognition system is an application of computer vision and image processing technology that takes photograph of vehicles as input image and by extracting their number plate from whole vehicle image , it display the number plate information into text. Mainly the ANPR system consists of 4 phases: Acquisition of Vehicle Image and PreProcessing, Extraction of Number Plate Area, Character Segmentation and Character Recognition. The overall accuracy and efficiency of whole ANPR system depends on number plate extraction phase as character segmentation and character recognition phases are also depend on the output of this phase. Further the accuracy of Number Plate Extraction phase depends on the quality of captured vehicle image. Higher be the quality of captured input vehicle image more will be the chances of proper extraction of vehicle number plate area. The existing methods of ANPR works well for dark and bright/light categories image but it does not work well for Low Contrast, Blurred and Noisy images and the detection of exact number plate area by using the existing ANPR approach is not successful even after applying existing filtering and enhancement technique for these types of images. Due to wrong extraction of number plate area, the character segmentation and character recognition are also not successful in this case by using the existing method. To overcome these drawbacks I proposed an efficient approach for ANPR in which the input vehicle image is pre-processed firstly by iterative bilateral filtering , adaptive histogram equalization and number plate is extracted from pre-processed vehicle image using morphological operations, image subtraction, image binarization/thresholding, sobel vertical edge detection and by boundary box analysis. Sometimes the extracted plate area also contains noise, bolts, frames etc. So the extracted plate area is enhanced by using morphological operations to improve the quality of extracted plate so that the segmentation phase gives more successful output. The character segmentation is done by connected component analysis and boundary box analysis and finally in the last character recognition phase, the characters are recognized by matching with the template database using correlation and output results are displayed. This approach works well for low contrast, blurred, noisy as well as for dark and light/bright category images. The comparison is done between the ANPR with Adaptive Histogram Equalization and Iterative Bilateral Filtering that is the proposed approach and the existing ANPR approach using metrics: MSE, PSNR and Success rate.

Façade image recognition under complex illumination conditions is crucial for various applications, including urban three-dimensional modeling and building identification. Existing methods relying solely on Red-Green-Blue (RGB) images are prone to texture ambiguity in complex illumination environments. Furthermore, façades display varying orientations and camera viewing angles, resulting in performance issues within the RGB color space. In this study, we introduce an illumination-invariant façade recognition network (I2-FaçadeNet) that leverages sparsely gated multi-color space experts for enhanced façade image recognition in challenging illumination environments. First, RGB façade images are converted into multi-color spaces to eliminate the ambiguous texture in complex illumination. Second, we train expert networks using separate channels of multi-color spaces. Finally, a sparsely gated mechanism is introduced to manage the expert networks, enabling dynamic activation of expert networks and the merging of results. Experimental evaluations leveraging both the International Society for Photogrammetry and Remote Sensing benchmark data sets and the Shenzhen data sets reveal that our proposed I2 -FaçadeNet surpasses various depths of ResNet in façade recognition under complex illumination conditions. Specifically, the classification accuracy for poorly illuminated façades in Zurich improves by nearly 8%, while the accuracy for over-illuminated areas in Shenzhen increases by approximately 3%. Moreover, ablation studies conducted on façade images with complex illumination indicate that compared to traditional RGB-based ResNet, the proposed network achieves an accuracy improvement of 3% to 4% up to 100% for overexposed images and an accuracy improvement of 3% to 10% for underexposed images.

License plate recognition is an essential task in applications like urban vehicle management, intelligent transportation system, traffic surveillance and parking management system. In this work, we acquire the images using the mobile app and recognize license plate details with the help of our proposed image processing model. The recognized license plate details have been displayed on a customized website. The proposed image processing model does the adaptive thresholding on the images with resolution of 1280× 960. The connected component analysis using bounding boxes will be performed on threshold image. The desired plate details are highlighted by creating a region of interest for maximum magnitude row of an image based on the pixel value, then the statistical and logical operations are used to extract the candidate region. After obtaining candidate region, recognition of license plate number has been done using template matching. The complete customer details, displayed on the customized website which is connected to the database with the help of plate number. The computation time of proposed method is less than the existed methods.

Potato leaf diseases are recognized as a major threat to agricultural productivity and global food security, emphasizing the need for rapid and accurate detection methods. Conventional manual diagnosis is limited by inefficiency and susceptibility to bias, whereas existing automated approaches are often constrained by insufficient feature extraction, inadequate integration of multiple leaves, and poor generalization under complex field conditions. To overcome these challenges, a ResNet18-SAWF model was developed, integrating a self-attention mechanism with a multi-scale feature-fusion strategy within the ResNet18 framework. The self-attention module was designed to enhance the extraction of key features, including leaf color, texture, and disease spots, while the feature-fusion module was implemented to improve the holistic representation of multi-leaf structures under complex backgrounds. Experimental evaluation was conducted using a comprehensive dataset comprising both simple and complex background conditions. The proposed model was demonstrated to achieve an accuracy of 98.36% on multi-leaf images with complex backgrounds, outperforming baseline ResNet18 (91.80%), EfficientNet-B0 (86.89%), and MobileNet_V2 (88.53%) by 6.56, 11.47, and 9.83 percentage points, respectively. Compared with existing methods, superior performance was observed, with an 11.55 percentage point improvement over the average accuracy of complex background studies (86.81%) and a 0.7 percentage point increase relative to simple background studies (97.66%). These results indicate that the proposed approach provides a robust, accurate, and practical solution for potato leaf disease detection in real field environments, thereby advancing precision agriculture technologies.

Deep convolution neural networks constitute a breakthrough in computer vision. Based on this, the Convolutional Neural Network (CNN) models offer enormous potential for crop disease classification. However, significant training data are required to realize their potential. In the case of crop disease image recognition, especially with complex backgrounds, it is sometimes difficult to acquire adequately labeled large datasets. This research proposed a solution to this problem that integrates multi-attention modules, i.e., channel and position block (CPB) module. Given an intermediate feature map, the CPB module can infer attention maps in parallel with the channel and position. The attention maps can then be multiplied to form input feature maps for adaptive feature refinement. This provides a simple yet effective intermediate attention structure for CNNs. The module is also lightweight and produces little overhead. Some experiments on cucumber and rice image datasets with complex backgrounds were conducted to validate the effectiveness of the CPB module. The experiments included different module locations and class activation map display characteristics. The classification accuracy reached 96.67% on the cucumber disease image dataset and 95.29% on the rice disease image dataset. The results show that the CPB module can effectively classify crop disease images with complex backgrounds, even on small-scale datasets, which providing a reference for crop disease image recognition method under complex background conditions in the field. Keywords: image recognition, crop disease, multi-attention module, deep learning, small sample DOI: 10.25165/j.ijabe.20251801.8136 Citation: Chen L, Yuan Y, He H Y. Image recognition for crop diseases using a novel multi-attention module. Int J Agric & Biol Eng, 2025; 18(1): 238–244.

Number plate detection plays a crucial role in various applications such as traffic monitoring, vehicle identification, and law enforcement.In recent years, advancements in computer vision and Machine Learning Techniques have revolutionized Number plate recognition systems.This paper proposes a location-based Number plate detection method that combines K-Nearest Neighbors Algorithm(KNN) and Optical Character Recognition (OCR) to accurately detect and recognize Number plates in real-time.The proposed system consists main stages: Number plate localization and Number plate recognition.In the first stage, a KNN-based approach is utilized to detect the presence and location of Number plates within an input image.The KNN model is trained using a large dataset of annotated images, enabling it to learn the distinctive features and patterns associated with Number plates.This stage aims to accurately identify the regions of interest containing Number plates, even in challenging scenarios such as varying lighting conditions, occlusions, and complex backgrounds.

Urban trees provide important ecosystem services to improve cities’ liveability and sustainability. Leaf chlorophyll content (Cab) estimation by remote sensing can help monitor tree health efficiently. However, the Cab retrieval of urban trees is challenging because of the complex canopy structures, backgrounds, and illuminations conditions. This paper proposed an automatic method for partitioning sunlit/shaded pixels and removal of bright-specular/dark-hole and background pixels. In addition, we proposed a new index, the Urban Tree Chlorophyll Index (UTCI), defined as UTCI=(ρ709-ρ697)/(ρ709-ρ686), based on the simulated hyperspectral images of urban tree using radiative transfer model. This proposed UTCI index outperforms existing narrow-band indices (NBIs) for estimating Cab for complex canopy structures, backgrounds, and illumination conditions evaluated using simulated hyperspectral images. The advantage of the UTCI was also demonstrated when applied to UAV hyperspectral images validated with direct field foliar measurements of Cab. It surpasses existing NBIs, demonstrating a moderate correlation (R2 = 0.34) with Cab under varying irradiance and a strong correlation (R2 = 0.62) with Cab under stable diffuse illumination. This study, for the first time, extensively investigated NBIs for Cab estimation of urban trees from UAV hyperspectral images, providing a theoretical and operational basis for future monitoring of Cab in the management of urban trees. This new method can be potentially applied to other vegetation types with complex canopy structures, backgrounds, and illuminations conditions.

This paper proposes a robust motion detection method for illumination variations which uses histogram of oriented gradients. The detection process is divided into two phases: coarse detection and refinement. In the coarse detection phase, first, a texture-based background model is built which implements a group of adaptive histograms of oriented gradients; then, by comparing the histogram of oriented gradients of each pixel between current frame and background model, a foreground is segmented based on texture feature which is not susceptible to illumination variations, whereas some missing foreground regions exist; finally, the result based on texture is optimized by combining the pixel-wise detection result produced by Gaussian Mixture Model (GMM) algorithm, which greatly improves the detection performance by incorporating efficient morphological operations. In the refinement phase, the above detection result is refined based on the distinction in color feature to eliminate errors like shadows, noises, redundant contour, etc. Experimental results show the effectiveness and robustness of our approach in detecting moving objects in varying illumination conditions.

We improved classic retinal modeling to alleviate the adverse effect of complex illumination on face recognition and extracted robust image features. Our improvements on classic retinal modeling included three aspects. First, a combined filtering scheme was applied to simulate functions of horizontal and amacrine cells for accurate local illumination estimation. Second, we developed an optimal threshold method for illumination classification. Finally, we proposed an adaptive factor acquisition model based on the arctangent function. Experimental results on the combined Yale B; the Carnegie Mellon University poses, illumination, and expression; and the Labeled Face Parts in the Wild databases show that the proposed method can effectively alleviate illumination difference of images under complex illumination conditions, which is helpful for improving the accuracy of face recognition and that of facial feature point detection.

The DM (Data Matrix) two-dimensional barcode images collected on metal parts with complex lighting conditions are prone to low contrast and local shadow, and the problem of uneven brightness leads to the loss of two-dimensional barcode information, which brings difficulties to the subsequent processing. However, the existing binarization algorithms will have the problems of too much noise and long segmentation time when dealing with this kind of images. To solve these problems, an improved local threshold algorithm is proposed to improve the anti-noise performance and computational efficiency. First of all, the algorithm model is improved to reduce the sensitivity to noise, and then the integral image algorithm is used to speed up the calculation of the local mean. In addition, the gray value of the local central pixel and the local mean are used to adjust the threshold adaptively according to the gray change characteristics of each pixel neighborhood, so as to further improve the segmentation efficiency. The improved local threshold algorithm and other five algorithms are tested on images with complex illumination conditions. The results show that the improved local threshold algorithm can not only effectively overcome the influence of complex illumination, has a good anti-noise effect, but also greatly shorten the time of image segmentation.