Smart manufacturing enables an efficient manufacturing process by optimizing production and product transaction. The optimization is performed through data analytics that requires reliable and informative data as input. Therefore, in this paper, an accurate data capture approach based on a vision sensor is proposed. Three image recognition methods are studied to determine the best vision-based classification technique, namely Bag of Words (BOW), Spatial Pyramid Matching (SPM) and Convolutional Neural Network (CNN). The vision-based classifiers categorize the apple as defective and non-defective that can be used for automatic inspection, sorting and further analytics. A total of 550 apple images are collected to test the classifiers. The images consist of 275 non-defective and 275 defective apples. The defective category includes various types of defect and severity. The vision-based classifiers are trained and evaluated according to the K-fold cross-validation. The performances of the classifiers from 2-fold, 3-fold, 4-fold, 5-fold and 10-fold are compared. From the evaluation, SPM with SVM classifier attained 98.15% classification accuracy for 10-fold and outperformed the others. In terms of computational time, CNN with SVM classifier is the fastest. However, minimal time difference is observed between the computational time of CNN and SPM, which were separated by only 0.05 s.
Taking into consideration that the prior CMF detection methods rely on several fixed threshold values in the filtering process, we propose an efficient CMF detection method with an automatic threshold selection, named as CMF-iteMS. The CMF-iteMS recommends a PatchMatch-based CMF detection method that adapts Fourier-Mellin Transform (FMT) as the feature extraction technique while a new automatic threshold selection based on iterative means of regions size (iteMS) procedure is introduced to have flexibility in changing the threshold value for various characteristics (quality, sizes, and attacks) in each input image. To ensure the reliability of the proposed CMF-iteMS, the method is compared with four state-of-the-art CMF detection methods based on Scale Invariant Feature Transform (SIFT), patch matching, multi-scale analysis and symmetry techniques using three available datasets that cover the variety of characteristics in CMF images. The results show that the F-score of the CMF-iteMS outperformed existing CMF detection methods by exceeding an average of 90% F-score values for image-level evaluation and 82% of F-score value for pixel-level evaluation for all datasets in original size. As special attention is given to the image resizing attack, the method is able to maintain the highest performance even if the images in the datasets are resized to 0.25 parameter.
The domain of underwater wireless sensor networks (UWSNs) had received a lot of attention recently due to its significant advanced capabilities in the ocean surveillance, marine monitoring and application deployment for detecting underwater targets. However, the literature have not compiled the state-of-the-art along its direction to discover the recent advancements which were fuelled by the underwater sensor technologies. Hence, this paper offers the newest analysis on the available evidences by reviewing studies in the past five years on various aspects that support network activities and applications in UWSN environments. This work was motivated by the need for robust and flexible solutions that can satisfy the requirements for the rapid development of the underwater wireless sensor networks. This paper identifies the key requirements for achieving essential services as well as common platforms for UWSN. It also contributes a taxonomy of the critical elements in UWSNs by devising a classification on architectural elements, communications, routing protocol and standards, security, and applications of UWSNs. Finally, the major challenges that remain open are presented as a guide for future research directions.
A hot spot problem is a problem where cluster nodes near to the base station (BS) tend to drain their energy much faster than other nodes due to the need to perform more communication. Unequal clustering methods such as unequal clustering routing (UDCH) and energy-efficient fuzzy logic for unequal clustering (EEFUC) have been proposed to address this problem. However, these methods only concentrate on utilizing residual energy and the distance of sensor nodes to the base station, while limited attention is given to enhancing the data transmission process. Therefore, this paper proposes an energy-efficient unequal clustering scheme based on a balanced energy method (EEUCB) that utilizes minimum and maximum distance to reduce energy wastage. Apart from that, the proposed EEUCB also utilizes the maximum capacity of node energy and double cluster head technique with a sleep-awake mechanism. Furthermore, EEUCB has devised a clustering rotation strategy based on two sub-phases, namely intra- and inter-clustering techniques, that considers the average energy threshold, average distance threshold, and BS layering node. The performance of the proposed EEUCB protocol is then compared with various prior techniques. From the result, it can be observed that the proposed EEUCB protocol shows lifetime improvements of 57.75%, 19.63%, 14.7%, and 13.06% against low-energy adaptive clustering hierarchy (LEACH), factor-based LEACH FLEACH, EEFUC, and UDCH, respectively.
Fruits are mature ovaries of flowering plants that are integral to human diets, providing essential nutrients such as vitamins, minerals, fiber and antioxidants that are crucial for health and disease prevention. Accurate classification and segmentation of fruits are crucial in the agricultural sector for enhancing the efficiency of sorting and quality control processes, which significantly benefit automated systems by reducing labor costs and improving product consistency. This paper introduces the "FruitSeg30_Segmentation Dataset & Mask Annotations", a novel dataset designed to advance the capability of deep learning models in fruit segmentation and classification. Comprising 1969 high-quality images across 30 distinct fruit classes, this dataset provides diverse visuals essential for a robust model. Utilizing a U-Net architecture, the model trained on this dataset achieved training accuracy of 94.72 %, validation accuracy of 92.57 %, precision of 94 %, recall of 91 %, f1-score of 92.5 %, IoU score of 86 %, and maximum dice score of 0.9472, demonstrating superior performance in segmentation tasks. The FruitSeg30 dataset fills a critical gap and sets new standards in dataset quality and diversity, enhancing agricultural technology and food industry applications.
Retinal image registration is important to assist diagnosis and monitor retinal diseases, such as diabetic retinopathy and glaucoma. However, registering retinal images for various registration applications requires the detection and distribution of feature points on the low-quality region that consists of vessels of varying contrast and sizes. A recent feature detector known as Saddle detects feature points on vessels that are poorly distributed and densely positioned on strong contrast vessels. Therefore, we propose a multiresolution difference of Gaussian pyramid with Saddle detector (D-Saddle) to detect feature points on the low-quality region that consists of vessels with varying contrast and sizes. D-Saddle is tested on Fundus Image Registration (FIRE) Dataset that consists of 134 retinal image pairs. Experimental results show that D-Saddle successfully registered 43% of retinal image pairs with average registration accuracy of 2.329 pixels while a lower success rate is observed in other four state-of-the-art retinal image registration methods GDB-ICP (28%), Harris-PIIFD (4%), H-M (16%), and Saddle (16%). Furthermore, the registration accuracy of D-Saddle has the weakest correlation (Spearman) with the intensity uniformity metric among all methods. Finally, the paired t-test shows that D-Saddle significantly improved the overall registration accuracy of the original Saddle.