Deep Learning-based Feature Extraction Research Articles

Deep learning-based visual recognition of rumex for robotic precision farming

In this paper we address the problem of recognising the Broad-leaved dock (Rumex obtusifolius L.) in grasslands from high-resolution 2D images. We discuss and present the determining factors for developing and implementing weed visual recognition algorithms using deep learning. This analysis, leads to the formulation of the proposed algorithm. Our implementation exploits Transfer Learning techniques for deep learning-based feature extraction, in combination with a classifier for weed recognition. A prototype robotic platform has been used to make available an image dataset from a dairy farm containing broad-leaved docks. The evaluation of the proposed algorithm on this dataset shows that it outperforms competing weed/plant recognition methods in recognition accuracy, while producing low false-positive rates under real-world operation conditions.

A hybrid deep learning–based model for automatic car extraction from high-resolution airborne imagery

Automatic car extraction (ACE) from high-resolution airborne imagery (i.e., true-orthophoto) has been a hot research topic in the field of photogrammetry and machine learning. ACE from high-resolution airborne imagery is the most suitable method for control and monitoring practices in large cities such as traffic management. The use of deep learning–based feature extraction methods, such as convolutional neural networks, have been providing state-of-the-art performance in the last few years, particularly, these techniques have been successfully applied to automatic object extraction from images. In this paper, we proposed a novel hybrid method to take advantage of the semantic segmentation of high-resolution airborne imagery to ACE that is realized based on the combination of deep convolutional neural networks and restricted Boltzmann machine (RBM). This hybrid method is called RBMDeepNet. We trained and tested our model on the ISPRS Potsdam and Vaihingen benchmark datasets (non-big data) which is more challenging for ACE. Here, Potsdam data is a true-color dataset, and Vaihingen data is a false-color dataset. The results obtained in the present study showed that the proposed method for ACE from high-resolution airborne imagery achieves a 7% improvement in accuracy with about 10% improvement in processing time compared to similar methods.

Prediction of biomarker status, diagnosis and outcome from histology slides using deep learning-based hypothesis free feature extraction.

3140 Background: Recently, histological pattern signatures obtained from diagnostic H&E images have been found to predict mutation, biomarker status or outcome. We report here on a novel deep learning based framework designed to identify and extract predictive histological signatures. We have applied this framework in 3 experiments, predicting specifically the microsatellite status (MSS) of colorectal cancer (CRC), breast cancer (BC) micrometastasis in Lymph nodes (LN) and Pathologic Complete Response (pCR) in BC diagnostic biopsies. Methods: Our deep learning based algorithm was trained on histology images at 20X magnification. Algorithms were trained for binary classification for each of the three cohorts. We used 75% of the images for training and test our algorithm on the remaining 25% of the images. Cohort details are as follows: MSS for CRC: 94 patients’ H&E stained tissue images from the Roche internal CRC80 dataset (MSS n =24; MSI n = 70) were used. BC LN: 270 patients’ H&E stained tissue images from the CAMELYON16 dataset ( LN(+) n = 110 ; LN(-), n =160) were used. pCR for BC: 225 patients’ H&E stained tissue images from the Tryphaena Study BO22280, neoadjuvant, Trastuzumab/Pertuzumab chemotherapy combination trial. (pCR=111, non-pCR n=114). Results: We report and assess algorithm performance on each of the cohorts by Area Under the Curve (AUC). Prediction of MSS in the CRC80 status yielded AUC 0.9. Prediction of LN invasion on CAMELYON16 dataset yielded AUC 0.85. Prediction of pCR on the Tryphaena cohort yielded an AUC of 0.8. Conclusions: We present a new approach to generate predictive signatures based on conventional diagnostic H&E images and a novel machine learning framework. The CRC80 and CAMELYON16 cohorts served as a confidence building experiments with predictive features well known by clinicians and visually confirmed. The predictive algorithm for pCR in the Tryphaena cohort yielded both response prediction and the high predictive value FOVs. These included tissue patterns which have not until now been considered to influence on the prediction of pCR.

Accurate Speech Emotion Recognition by using Brain-Inspired Decision-Making Spiking Neural Network

A portion of speech recognition is taken away by emotion recognition which is a smart update and it is necessary for its gain massively. Feature selection is an indispensable stage among the furtherance of various schemes in order to implement the classification of sentiments in speaking. The communication among features prompted from the alike audio origin has been rarely deliberated at present, which might yield terminated features and cause an upswing in the computational costs. To resolve these defects the deep learning-based feature extraction technique is used. An incredible modernization in speech recognition in recent years incorporates machine learning techniques with a deep structure for feature extraction. In this paper, the speech signal obtained from the SAVEE database is used as an input for a deep belief network. In order to perform pre-training in the network, the layer-wise rapacious feature extraction tactic is implemented and by using systematic samples, the smearing back-propagation method is accomplished for attaining fine-tuning. Brain-inspired decision-making spiking neural network (SNNs) is used to recognize different emotions but training by deep SNNs remains a challenge, but it improves the determination of the result. In order to enhance the parameters of SNNs, a social ski-driver (SSD) evolutionary optimization algorithm is used. The results of the SNN-SSD algorithm are related to artificial neural networks and long short term memory with different emotions to refine the classification for authorization.

A Deep Feature Extraction Method for HEp-2 Cell Image Classification

The automated and accurate classification of the images portraying the Human Epithelial cells of type 2 (HEp-2) represents one of the most important steps in the diagnosis procedure of many autoimmune diseases. The extreme intra-class variations of the HEp-2 cell images datasets drastically complicates the classification task. We propose in this work a classification framework that, unlike most of the state-of-the-art methods, uses a deep learning-based feature extraction method in a strictly unsupervised way. We propose a deep learning-based hybrid feature learning with two levels of deep convolutional autoencoders. The first level takes the original cell images as the inputs and learns to reconstruct them, in order to capture the features related to the global shape of the cells, and the second network takes the gradients of the images, in order to encode the localized changes in intensity (gray variations) that characterize each cell type. A final feature vector is constructed by combining the latent representations extracted from the two networks, giving a highly discriminative feature representation. The created features will be fed to a nonlinear classifier whose output will represent the type of the cell image. We have tested the discriminability of the proposed features on two of the most popular HEp-2 cell classification datasets, the SNPHEp-2 and ICPR 2016 datasets. The results show that the proposed features manage to capture the distinctive characteristics of the different cell types while performing at least as well as the actual deep learning-based state-of-the-art methods in terms of discrimination.

A deep learning based feature extraction method on hyperspectral images for nondestructive prediction of TVB-N content in Pacific white shrimp (Litopenaeus vannamei)

Hyperspectral imaging (HSI) technique with spectral range of 900–1700 nm was implemented to predict total volatile basic nitrogen (TVB-N) content in Pacific white shrimp. Successive projections algorithm (SPA) and deep-learning-based stacked auto-encoders (SAEs) algorithm were comparatively used for spectral feature extraction. Least-squares support vector machine (LS-SVM), partial least squares regression (PLSR) and multiple linear regression (MLR) were used for prediction. The results demonstrated that the SAEs-based prediction models (SAEs-LS-SVM, SAEs-MLR and SAEs-PLSR) performed better than either full wavelengths-based or SPA-based prediction models. The SAEs-LS-SVM was considered to be the best model with RP2 value of 0.921, RMSEP value of 6.22 mg N [100 g]−1, RPD value of 3.58 and computational time of 3.9 ms for predicting TVB-N in prediction set. The results of this study indicated that SAEs has a high potential in the multivariate analysis of hyperspectral images for shrimp quality inspections.

Real-Time Headgear Detection in Videos Using Deep Learning Based Feature Extraction with A Supervised Classifier

Real-Time Headgear Detection in Videos Using Deep Learning Based Feature Extraction with A Supervised Classifier

Real-Time Headgear Detection in Videos Using Deep Learning Based Feature Extraction with A Supervised Classifier - ADCOM 2018

This paper presents an approach for detection of headgear in real-time video footages. The approach used is Feature Extraction followed by Classification. To pick specific features required for the aforesaid problem, a pre-trained deep learning model is used.

Deep learning feature extraction for multispectral palmprint identification

Person’s identity validation is becoming much more essential due to the increasing demand for high-security systems. A biometric system testifies the authenticity of specific physiological or behavioral characteristics-based biometric technology. This technology has been successfully applied to verification and identification systems. We analyze the multispectral palmprint biometric identification system in unimodal and multimodal modes. In an identification system, the feature extraction is a crucial step. For this reason, we propose an efficient deep learning feature extraction algorithm called discrete cosine transform network (DCTNet). The effectiveness of the proposed approach has been evaluated on two publicly available databases: CASIA and PolyU. The obtained results clearly indicate that the DCTNet deep learning-based feature extraction technique can achieve comparable performance to the best of the state-of-the-art techniques.

Multi-retinal disease classification by reduced deep learning features

This paper presents the retina-based disease diagnosis through deep learning-based feature extraction method. This process helps in developing automated screening system, which is capable of diagnosing retina for diseases such as age-related molecular degeneration, diabetic retinopathy, macular bunker, retinoblastoma, retinal detachment, and retinitis pigmentosa. Some of these diseases share a common characteristic, which makes the classification difficult. In order to overcome the above-mentioned problem, deep learning feature extraction and a multi-class SVM classifier are used. The main contribution of this work is the reducing the dimension of the features required to classify the retinal disease, which enhances the process of reducing the system requirement as well as good performance.