As an important branch in the field of image fusion, the multi-focus image fusion technique can effectively solve the problem of optical lens depth of field, making two or more partially focused images fuse into a fully focused image. In this paper, the methods based on boundary segmentation was put forward as a group of image fusion method. Thus, a novel classification method of image fusion algorithms is proposed: transform domain methods, boundary segmentation methods, deep learning methods, and combination fusion methods. In addition, the subjective and objective evaluation standards are listed, and eight common objective evaluation indicators are described in detail. On the basis of lots of literature, this paper compares and summarizes various representative methods. At the end of this paper, some main limitations in current research are discussed, and the future development of multi-focus image fusion is prospected.
Tenbrio molitor (T. molitor) is a widely utilized feed ingredient, though it is deficient in long-chain omega-3 fatty acids, such as eicosapentaenoic acid (EPA) and docosahexaenoic acid (DHA). To address this, dietary supplements containing EPA and DHA in ethyl ester and triglyceride forms were administered to investigate the lipid metabolism and bioenhancement potential of T. molitor. The larvae exhibited normal growth across all treatment groups. EPA/DHA levels were significantly elevated in T. molitor-enriched diets, with newly identified phospholipid species including phosphatidylcholine 18:1_20:5 (PC 18:1_20:5) and phosphatidylethanolamine 18:0_20:5 (PE 18:0_20:5). KEGG pathway analysis revealed that glycerol phospholipid metabolism (ko00564), endogenous cannabinoid signaling (ko04723), and cell division (ko04148) were the core pathways that promoted phospholipid synthesis and oxidative lipid conversion (such as peroxide value-phosphatidylcholine, POV-PC). T. molitor activates glycerophospholipid metabolism, converting EPA/DHA into more bioavailable medium- and short-chain phospholipids, thereby enhancing its nutritional value and providing a new strategy for the development of functional foods/feeds.
Due to their high nutritional value and a lower environmental impact, Tenebrio molitor (T. molitor) larvae are regarded as an alternative protein and lipid source in food industries, animal husbandry, and fishery. This study aimed to investigate the effect of ω-3 PUFA intake on the nutritional value and gut microbiota of T. molitor larvae. Tenebrio molitor (T. molitor) larvae were reared with wheat bran at 20–32 °C for 4 weeks to screen for a suitable temperature. EPA ethyl esters (EE), DHA ethyl esters (ED), DHA triglycerides (TG), and krill oil (KO) were supplemented in wheat bran to rear larvae for 4 weeks, and the compositions including moisture, carbohydrates, crude protein, and crude fats were analyzed. Gut microbiome was analyzed using 16S rRNA amplicon sequencing. Larvae reared on wheat bran showed optimal growth at 28 °C. ω-3 PUFA supplements increased crude protein (1.07–1.16 fold) and crude fat (1.12–1.22 fold) contents without affecting survival. Gut microbiota composition shifted significantly in all ω-3 supplemented groups, altering over 10 genera. Bacteria with changed abundance (e.g., Clostridium), known for roles in protein/lipid metabolism, likely contributed to the enhanced nutritional contents. These findings demonstrate the benefits of ω-3 PUFA supplementation in T. molitor rearing and identify associated gut bacteria.
The fabric defect models based on deep learning often demand numerous training samples to achieve high accuracy. However, obtaining a complete dataset containing all possible fabric textures and defects is a big challenge due to the sophisticated and various fabric textures and defect forms. This study created a two-stage deep pix2pixGAN network called Dual Deep pix2pixGAN Network (DPGAN) to address the above problem. The defect generation model was trained based on the DPGAN network to automatically “transfer” defects from defected fabric images to clean, defect-free fabric images, thus strengthening the training data. To evaluate the effectiveness of the defect generation model, extensive comparative experiments were conducted to assess the performance of the fabric defect detection before and after data enhancement. The results indicate that the detection accuracy was improved regarding the belt_yarn, hole, and stain defect.