A review of cancer data fusion methods based on deep learning

Information Fusion, Год журнала: 2024, Номер 108, С. 102361 - 102361

Опубликована: Март 20, 2024

Язык: Английский

---

LCDDN-YOLO: Lightweight Cotton Disease Detection in Natural Environment, Based on Improved YOLOv8

Agriculture, Год журнала: 2025, Номер 15(4), С. 421 - 421

Опубликована: Фев. 17, 2025

To address the challenges of detecting cotton pests and diseases in natural environments, as well similarities features exhibited by diseases, a Lightweight Cotton Disease Detection Natural Environment (LCDDN-YOLO) algorithm is proposed. The LCDDN-YOLO based on YOLOv8n, replaces part convolutional layers backbone network with Distributed Shift Convolution (DSConv). BiFPN incorporated into original architecture, adding learnable weights to evaluate significance various input features, thereby enhancing detection accuracy. Furthermore, it integrates Partial (PConv) (DSConv) C2f module, called PDS-C2f. Additionally, CBAM attention mechanism neck improve model performance. A Focal-EIoU loss function also integrated optimize model’s training process. Experimental results show that compared YOLOv8, reduces number parameters 12.9% floating-point operations (FLOPs) 9.9%, while precision, mAP@50, recall 4.6%, 6.5%, 7.8%, respectively, reaching 89.5%, 85.4%, 80.2%. In summary, offers excellent accuracy speed, making effective for pest disease control fields, particularly lightweight computing scenarios.

Язык: Английский

---

MDFF-Net: A multi-dimensional feature fusion network for breast histopathology image classification

Computers in Biology and Medicine, Год журнала: 2023, Номер 165, С. 107385 - 107385

Опубликована: Авг. 16, 2023

Язык: Английский

---

Feature extraction of multimodal medical image fusion using novel deep learning and contrast enhancement method

Applied Intelligence, Год журнала: 2024, Номер 54(7), С. 5907 - 5930

Опубликована: Апрель 1, 2024

Язык: Английский

---

Mathematical modeling and simulation of multi-focus image fusion techniques using the effect of image enhancement criteria: a systematic review and performance evaluation

Artificial Intelligence Review, Год журнала: 2023, Номер 56(11), С. 13787 - 13839

Опубликована: Апрель 19, 2023

Язык: Английский

---

Infrared and visible image fusion using quantum computing induced edge preserving filter

Image and Vision Computing, Год журнала: 2024, Номер unknown, С. 105344 - 105344

Опубликована: Ноя. 1, 2024

Язык: Английский

---

Hilbert Vibration Decomposition and Multiple Filtering with Pre-Enhancement-Based Image Fusion Technique

National Academy Science Letters, Год журнала: 2025, Номер unknown

Опубликована: Янв. 16, 2025

Язык: Английский

---

A Computational and Comparative Analysis of Medical Image Fusion Using Different Transform Domain Techniques

Lecture notes in networks and systems, Год журнала: 2024, Номер unknown, С. 165 - 186

Опубликована: Янв. 1, 2024

Язык: Английский

---

Adaptive decomposition with guided filtering and Laplacian pyramid-based image fusion method for medical applications

Deleted Journal, Год журнала: 2024, Номер 6(8)

Опубликована: Авг. 1, 2024

Abstract Medical image fusion enhances diagnostic precision and facilitates clinical decision-making by integrating information from multiple medical imaging modalities. However, this field is still challenging as the output integrated image, whether spatial or transform domain algorithms, may suffer drawbacks such low contrast, blurring effect, noise, over smoothness, etc. Also, some existing novel works are restricted to specific datasets. So, address issues, a new multi-modal approach based on advantageous effects of transforms has been introduced in present work. For this, we use an adaptive decomposition tool known Hilbert vibration (HVD). HVD decomposes into different energy components, after proper source images, desirable features decomposed components then passed through guided filter (GF) for edge preservation. Then, Laplacian pyramid integrates these filtered parts using choose max rule. Since offers better resolution independent fixed cut-off frequencies like other transforms, subjective outputs method publicly available datasets clear than previously 20 state-of-the-art published results. Moreover, obtained values objective evaluation metrics entropy ( IE ): 7.6943, 5.9737, mean: 110.6453, 54.6346, standard deviation SD 85.5376, 61.8129, average gradient AG 109.2818, 64.6451, frequency SF 0.1475, 0.1100, metric Q HK/S 0.5400, 0.6511 demonstrate its comparability others. The algorithm's running period just 0.161244 s also indicates high computational efficiency.

Язык: Английский

---

A fine-grained recognition technique for identifying Chinese food images

Heliyon, Год журнала: 2023, Номер 9(11), С. e21565 - e21565

Опубликована: Ноя. 1, 2023

As a crucial area of research in the field computer vision, food recognition technology has become core many food-related fields, such as unmanned restaurants and nutrition analysis, which are closely related to our healthy lives. Obtaining accurate classification results is most important task recognition. Food fine-grained process, involves extracting features from group objects with similar appearances accurately classifying them into different categories. In usage environment, network required not only overview overall image, but also capture subtle details within it. addition, since Chinese images have unique texture features, model needs extract information image. However, existing CNN methods focused on processed this information. To classify possible, paper introduces Laplace pyramid convolution layer proposes bilinear that can perceive image multi-scale (LMB-Net). The proposed was evaluated public dataset, demonstrate LMB-Net achieves state-of-the-art performance.

Язык: Английский

---