Deep CNNs for microscopic image classification by exploiting transfer learning and feature concatenation

Nguyen, Long D.; Lin, Dongyun; Lin, Zhiping; Cao, Jiuwen

doi:10.1109/iscas.2018.8351550

Cited by 225 publications

(106 citation statements)

References 33 publications

Supporting

Mentioning

105

Contrasting

Order By: Relevance

“…The InceptionResNetV2 network [24] was based on the Inceptionbased network structure and residual connections. InceptionResNetV2 performs nearly identically to Inception architectures, but this architecture achieved significant acceleration in training using residual connections [25].…”

Section: Deep Learning and Pretrained Cnn Modelsmentioning

confidence: 99%

Plant disease and pest detection using deep learning-based features

Türkoğlu¹,

Hanbay²

2019

Turk J Elec Eng & Comp Sci

213

View full text Add to dashboard Cite

The timely and accurate diagnosis of plant diseases plays an important role in preventing the loss of productivity and loss or reduced quantity of agricultural products. In order to solve such problems, methods based on machine learning can be used. In recent years, deep learning, which is especially widely used in image processing, offers many new applications related to precision agriculture. In this study, we evaluated the performance results using different approaches of nine powerful architectures of deep neural networks for plant disease detection. Transfer learning and deep feature extraction methods are used, which adapt these deep learning models to the problem at hand. The utilized pretrained deep models are considered in the presented work for feature extraction and for further fine-tuning. The obtained features using deep feature extraction are then classified by support vector machine (SVM), extreme learning machine (ELM), and K-nearest neighbor (KNN) methods. The experiments are carried out using data consisting of real disease and pest images from Turkey. The accuracy, sensitivity, specificity, and F1-score are all calculated for performance evaluation. The evaluation results show that deep feature extraction and SVM/ELM classification produced better results than transfer learning. In addition, the fc6 layers of the AlexNet, VGG16, and VGG19 models produced better accuracy scores when compared to the other layers.

show abstract

Section: Deep Learning and Pretrained Cnn Modelsmentioning

confidence: 99%

Plant disease and pest detection using deep learning-based features

Türkoğlu¹,

Hanbay²

2019

Turk J Elec Eng & Comp Sci

213

View full text Add to dashboard Cite

show abstract

“…In such a scenario, in order to leverage the power of CNNs and at the same time reduce the computational costs, transfer learning can be used 7,8 . In this approach, the CNN is initially pre-trained on a large and diverse generic image data set and then applied to a specific task 9 . There are several pre-trained neural networks that have won international competitions like VGGNet 10 , Resnet 11 , Nasnet 12 , Mobilenet 13 , Inception 14 and Xception 15 .…”

mentioning

confidence: 99%

Efficient Classification of White Blood Cell Leukemia with Improved Swarm Optimization of Deep Features

Sahlol

Kollmannsberger

Ewees

2020

Sci Rep

212

101

View full text Add to dashboard Cite

White Blood Cell (WBC) Leukaemia is caused by excessive production of leukocytes in the bone marrow, and image-based detection of malignant WBCs is important for its detection. Convolutional Neural Networks (CNNs) present the current state-of-the-art for this type of image classification, but their computational cost for training and deployment can be high. We here present an improved hybrid approach for efficient classification of WBC Leukemia. We first extract features from WBC images using VGGNet, a powerful CNN architecture, pre-trained on ImageNet. The extracted features are then filtered using a statistically enhanced Salp Swarm Algorithm (SESSA). This bio-inspired optimization algorithm selects the most relevant features and removes highly correlated and noisy features. We applied the proposed approach to two public WBC Leukemia reference datasets and achieve both high accuracy and reduced computational complexity. The SESSA optimization selected only 1 K out of 25 K features extracted with VGGNet, while improving accuracy at the same time. The results are among the best achieved on these datasets and outperform several convolutional network models. We expect that the combination of CNN feature extraction and SESSA feature optimization could be useful for many other image classification tasks.

show abstract

“…In the Inception-ResNet block, multiple sized convolutional filters are combined by residual connections. The usage of residual connections not only avoids the degradation problem caused by deep structures but also reduces the training time [81]. The 35 × 35, 17 × 17 and 8 × 8 grid modules, known as Inception-A, Inception-B and Inception-C blocks, are used in the Inception-ResNet-v2 network.…”

Section: Deep Learning Architectures For Semantic Segmentation -Vgg16mentioning

confidence: 99%

Semantic Segmentation of HeLa Cells: An Objective Comparison between one Traditional Algorithm and Three Deep-Learning Architectures

Karabağ

Jones

Peddie

et al. 2020

Preprint

View full text Add to dashboard Cite

In this work, images of a HeLa cancer cell were semantically segmented with one traditional image-processing algorithm and three deep learning architectures: VGG16, ResNet18 and Inception-ResNet-v2. Three hundred slices, each 2000 × 2000 pixels, of a HeLa Cell were acquired with Serial Block Face Scanning Electron Microscopy. The deep learning architectures were pre-trained with ImageNet and then fine-tuned with transfer learning. The image-processing algorithm followed a pipeline of several traditional steps like edge detection, dilation and morphological operators. The algorithms were compared by measuring pixel-based segmentation accuracy and Jaccard index against a labelled ground truth. The results indicated a superior performance of the traditional algorithm (Accuracy = 99%, Jaccard = 93%) over the deep learning architectures: VGG16 (93%, 90%), ResNet18 (94%, 88%), Inception-ResNet-v2 (94%, 89%).

show abstract

Deep CNNs for microscopic image classification by exploiting transfer learning and feature concatenation

Cited by 225 publications

References 33 publications

Plant disease and pest detection using deep learning-based features

Plant disease and pest detection using deep learning-based features

Efficient Classification of White Blood Cell Leukemia with Improved Swarm Optimization of Deep Features

Semantic Segmentation of HeLa Cells: An Objective Comparison between one Traditional Algorithm and Three Deep-Learning Architectures

Contact Info

Product

Resources

About