Biomedical compound figure detection using deep learning and fusion techniques

Graphical integrity issues in open access publications: Detection and patterns of proportional ink violations

“…Trying to fill this gap, we proposed our automated method to examine images at scale and to detect proportional ink violations with relatively high accuracy. Moreover, the components in this method can address compound figure classification and subfigure separation for other graphical integrity investigations, complementing previous research (e.g., [ 35 , 37 ]).…”

“…Researchers have proposed several methods to achieve this separation, either using traditional computer vision algorithms such as edge-based detection of spaces between panels [ 35 , 36 ]. Interestingly, similar to what has happened with chart extraction, subfigure separation has benefited and improved from new deep learning techniques and large annotated compound figure datasets [ 37 ]. Although there is still room to improve, subfigure separation is mature enough to be used in production systems such as Semantic Scholar.…”

Late fusion of deep learning and handcrafted visual features for biomedical image modality classification

“…The estimated posterior probabilities from SVM and softmax classifiers are used to perform late score‐based fusion using the ‘combSUM’, ‘combPROD’, ‘combMAX’, ‘combMED’ and ‘combMIN’ fusion operators. Classifier combinations across different CNN architectures are recorded in Table 3 as it was found to be effective in other similar articles [29, 46]. Table 4 investigates effects of combining deep learning and traditional hand‐crafted models.…”

“…Later attempts used transfer learning (mostly with ImageNet), sometimes with data augmentation to expand the available dataset [26, 27, 45]. Fusion was also applied to combinations of different pre‐trained CNN architectures to further improve classification performance [29, 45, 46].…”

Research on automatic location and recognition of insulators in substation based on YOLOv3

“…In 2012, the concept of deep learning gained prominence and achieved good results in the field of image processing, such as facial recognition and signal extraction. This led to some scholars applying and theorising on deep learning in other areas, such as the electric power and energy power fields [10, 11]. Among them, the application of deformable parts models [12], region‐based convolutional neural networks (RCNNs) [13], spatial pyramid pooling networks (SPPnets) [14] and fast RCNNs [15] are more popular, and equipment classification and diagnosis can be realised through optimisation algorithms and parameter tuning.…”