Fukunaga–Koontz Convolutional Network with Applications on Character Classification

Gatto, Bernardo B.; Santos, Eulanda M. dos; Fukui, Kiichi; Waldir, S. S.; Santos, Kenny

doi:10.1007/s11063-020-10244-5

Cited by 9 publications

(8 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, a thorough comparative study of multimodal problems using only SI algorithms including the aforementioned examples is due. Another research direction includes applying the proposed method for weight tuning of shallow networks [ 33 , 34 ]. Such networks may benefit from the proposed optimization mechanism since it tackles small sample size problems featuring rough objective function landscapes.…”

Section: Discussionmentioning

confidence: 99%

A-DVM: A Self-Adaptive Variable Matrix Decision Variable Selection Scheme for Multimodal Problems

Mollinetti

Gatto

Neto

et al. 2020

Entropy

View full text Add to dashboard Cite

Artificial Bee Colony (ABC) is a Swarm Intelligence optimization algorithm well known for its versatility. The selection of decision variables to update is purely stochastic, incurring several issues to the local search capability of the ABC. To address these issues, a self-adaptive decision variable selection mechanism is proposed with the goal of balancing the degree of exploration and exploitation throughout the execution of the algorithm. This selection, named Adaptive Decision Variable Matrix (A-DVM), represents both stochastic and deterministic parameter selection in a binary matrix and regulates the extent of how much each selection is employed based on the estimation of the sparsity of the solutions in the search space. The influence of the proposed approach to performance and robustness of the original algorithm is validated by experimenting on 15 highly multimodal benchmark optimization problems. Numerical comparison on those problems is made against the ABC and their variants and prominent population-based algorithms (e.g., Particle Swarm Optimization and Differential Evolution). Results show an improvement in the performance of the algorithms with the A-DVM in the most challenging instances.

show abstract

Section: Discussionmentioning

confidence: 99%

A-DVM: A Self-Adaptive Variable Matrix Decision Variable Selection Scheme for Multimodal Problems

Mollinetti

Gatto

Neto

et al. 2020

Entropy

View full text Add to dashboard Cite

show abstract

“…A convolution can exaggerate a feature through a local transformation, or convert an image into one that represents the feature more. The paper [6] describes some other shallow architectures that include convolutions. They suggest a new Fukunaga-Koontz network that would process images more orthogonally and locally, but with the more advanced neural network architecture.…”

Section: Related Workmentioning

confidence: 99%

“…Figure 1 is a nice example that gives the image parts generated for a number '4'. The scanning process makes use of the ideas of a continuous sequence and also convolutions [6][13], or producing an aggregated score from a region. The idea of cell associations was central to the first algorithm of [11] and subsequent work, and it is really only a count of what other cells are present when the cell in question is present.…”

Section: Image Partsmentioning

confidence: 99%

“…The process is intended to recognise image shapes, more than internal colours or textures, but this is still a difficult and challenging task. The tests of section 4 have been carried out on handwritten digit characters, and as noted in [6], handwritten character classification is fundamental in postal sorting, bank check recognition, automatic letter recognition, industrial automation, humancomputer interaction, and historical archive documents. Initial tests suggest that this new method is highly accurate and it fits well with an earlier cognitive model, and an ensemblehierarchy structure in particular.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Recognising Image Shapes from Image Parts, not Neural Parts

Greer¹

2022

Preprint

View full text Add to dashboard Cite

This paper describes an image processing method that makes use of image parts instead of neural parts. Neural networks excel at image or pattern recognition and they do this by constructing complex networks of weighted values that can cover the complexity of the pattern data. These features however are integrated holistically into the network, which means that they can be difficult to use in an individual sense. A different method might scan individual images and use a more local method to try to recognise the features in it. This paper suggests such a method, where a trick during the scan process can not only recognise separate image parts, as features, but it can also produce an overlap between the parts. It is therefore able to produce image parts with real meaning and also place them into a positional context. Tests show that it can be very accurate, scoring 100% on some handwritten digit test datasets. It also fits well with an earlier cognitive model, and an ensemble-hierarchy structure in particular.

show abstract

“…The typical CNN for processing images consists of convolutional filter layers mixed with pooling or data compression layers. The general process of CNN [ 13 ] is shown in Figure 1 . A convolution filter processes a small piece of the input image.…”

Section: Introductionmentioning

confidence: 99%

A Survey of Computer-Aided Tumor Diagnosis Based on Convolutional Neural Network

Yan

Yao

Wang

et al. 2021

Biology

View full text Add to dashboard Cite

Tumors are new tissues that are harmful to human health. The malignant tumor is one of the main diseases that seriously affect human health and threaten human life. For cancer treatment, early detection of pathological features is essential to reduce cancer mortality effectively. Traditional diagnostic methods include routine laboratory tests of the patient’s secretions, and serum, immune and genetic tests. At present, the commonly used clinical imaging examinations include X-ray, CT, MRI, SPECT scan, etc. With the emergence of new problems of radiation noise reduction, medical image noise reduction technology is more and more investigated by researchers. At the same time, doctors often need to rely on clinical experience and academic background knowledge in the follow-up diagnosis of lesions. However, it is challenging to promote clinical diagnosis technology. Therefore, due to the medical needs, research on medical imaging technology and computer-aided diagnosis appears. The advantages of a convolutional neural network in tumor diagnosis are increasingly obvious. The research on computer-aided diagnosis based on medical images of tumors has become a sharper focus in the industry. Neural networks have been commonly used to research intelligent methods to assist medical image diagnosis and have made significant progress. This paper introduces the traditional methods of computer-aided diagnosis of tumors. It introduces the segmentation and classification of tumor images as well as the diagnosis methods based on CNN to help doctors determine tumors. It provides a reference for developing a CNN computer-aided system based on tumor detection research in the future.

show abstract

Fukunaga–Koontz Convolutional Network with Applications on Character Classification

Cited by 9 publications

References 43 publications

A-DVM: A Self-Adaptive Variable Matrix Decision Variable Selection Scheme for Multimodal Problems

A-DVM: A Self-Adaptive Variable Matrix Decision Variable Selection Scheme for Multimodal Problems

Recognising Image Shapes from Image Parts, not Neural Parts

A Survey of Computer-Aided Tumor Diagnosis Based on Convolutional Neural Network

Contact Info

Product

Resources

About