The deep neural networks are capable of processing large amounts of data for image processing applications like classification, segmentation and identification etc. Conditional- Generative Adversarial Network (C-GAN) is an example of Deep Learning (DL)-based image processing algorithm that is used widely for identifying targets in images. In a Deep Learning based image processing application the quality of the input image plays an important role. The quality and variations within the dataset helps the neural network filters to derive the best features for the classification and identification of the target in the image. Many deep learning approaches will have a preprocessing pipeline which improves the quality of the input training data. The objective of this study was to evaluate the effect of preprocessing methods to improve C-GAN’s ability to detect epiphytes in images acquired by Unmanned Aerial Vehicles (UAVs). These methods include 1) trimming the training images to include mostly the target plant, 2) generating annotation images with a thresholding technique, and 3) incorporating binary cross entropy loss function. Results obtained from this study shows that the percent occupancy of input images and annotation method plays an important role in identifying the target plant.

Effect of Annotation and Loss Function on Epiphyte Identification using Conditional Generative Adversarial Network

COVID-19 pandemic has disrupted the normal functioning of the world at both the physical as well as biological level. Various biotechnological approaches form the core for finding the drug for COVID. But at the backend, it is highly supported by intensive computational algorithms for drug designing approaches. Artificial intelligence is one such area that can be used to mimic the living system by training it with multi-dimensional datasets. The rapid advancements in the field of artificial intelligence and machine learning have facilitated to build high-accurate generative models. Deep learning is a subset of artificial intelligence that is being used in the present study for ligand designing models. The results obtained by a deep learning-based model called variational autoencoder—general adversarial networks (VAE-GAN) show promising results in terms of ligand design and can also be utilized for drug repurposing. In this paper, we have attempted to build a VAE-GAN model which was trained on isomeric simplified molecular-input line-entry system (Iso-SMILES) data and molecular structure images of the COVID-19 drug dataset. The Iso-SMILES and molecular structure data analysis are useful, but the system needs more improvement to cater to the data loss in terms of spatial structures and orientation of the chemical compounds taken for the analysis. However, the system can be optimized with the help of higher hardware support and increased training datasets, which can help in more precise analysis for generating ligand molecules of interest. 

A Variational Autoencoder—General Adversarial Networks (VAE-GAN) Based Model for Ligand Designing

Classifiers selection based on analytic hierarchy process and similarity score for spam identification

Diabetic retinopathy (DR) is a complication of diabetes which is due to the impairment of blood vessels of photosensitive cells in the eyes. This complication results in loss of eyesight if not diagnosed in the early stages. There are five stages of diabetic retinopathy: No DR, mild, moderate, severe, and proliferative. DR detection by traditional methods consumes a lot of time. An automatic and precise model would require an adequate amount of data for training which is not available. Publicly available dataset is highly imbalanced for other classes apart from No DR, especially proliferative and severe classes. In this paper, a model is created in two stages. The first stage involves the generation of synthetic data points using Deep Convolutional Generative Adversarial Network (DCGAN). The synthetic data are for highly imbalanced classes namely severe and proliferative. The second phase involves the augmented data classification using a CNN architecture.

Classification of Class-Imbalanced Diabetic Retinopathy Images Using the Synthetic Data Creation by Generative Models

. High spatial resolution images acquired with drones can provide useful information to farmers for devising suitable management practices and increase crop yield. Data collected as individual frames or images have to be mosaiced using pattern recognition and matching process. Most flight missions collect hundreds of photos with high overlap and side overlap in order to generate mosaic without data gaps or distortion. These frames are aligned using the location information associated with each image. The same features are identified in multiple frames for generating the mosaic. In this process, it is common to use all or most of the images which requires a lot of resources. Uploading and processing hundreds of images could take several hours to days. Many farmers and crop consultants in developing countries may not have the necessary resources to upload hundreds of images. This study assessed the optimal number of images required to generate an image mosaic for a crop field without any data gaps or distortion. Images were collected at two different heights and directions. First, the mosaic was generated using all (100%) frames followed by subsets containing 90%, through 50% of images. Results obtained will assist us to plan the settings in future flight missions for acquiring optimal number of images required for generating image mosaic.

/pdf/optimizing-low-cost-uav-aerial-image-mosaicing-for-crop-4jx19hqz0u.pdf

Optimizing low-cost uav aerial image mosaicing for crop growth monitoring

. Unmanned Aerial Vehicle (UAV) missions often collect large volumes of imagery data. However, not all images will have useful information, or be of sufficient quality. Manually sorting these images and selecting useful data are both time consuming and prone to interpreter bias. Deep neural network algorithms are capable of processing large image datasets and can be trained to identify specific targets. Generative Adversarial Networks (GANs) consist of two competing networks, Generator and Discriminator that can analyze, capture, and copy the variations within a given dataset. In this study, we selected a variant of GAN called Conditional-GAN that incorporates an additional label parameter, for identifying epiphytes in photos acquired by a UAV in forests within Costa Rica. We trained the network with 70%, 80%, and 90% of 119 photos containing the target epiphyte, Werauhia kupperiana (Bromeliaceae) and validated the algorithm’s performance using a validation data that were not used for training. The accuracy of the output was measured using structural similarity index measure (SSIM) index and histogram correlation (HC) coefficient. Results obtained in this study indicated that the output images generated by C-GAN were similar (average SSIM = 0.89–0.91 and average HC 0.97–0.99) to the analyst annotated images. However, C-GAN had difficulty to identify when the target plant was away from the camera, was not well lit, or covered by other plants. Results obtained in this study demonstrate the potential of C-GAN to reduce the time spent by botanists to identity epiphytes in images acquired by UAVs.

/pdf/identifying-epiphytes-in-drones-photos-with-a-conditional-9nn35o58gj.pdf

Identifying epiphytes in drones photos with a conditional generative adversarial network (c-gan)

With the tremendous growth of the internet, cy-berspace is facing several threats from the attackers. Threats like spam emails account for 55% of total emails according to the Symantec monthly threat report. Over time, the attackers moved on to image spam to evade the text-based spam filters. To deal with this, the researchers have several machine learning and deep learning approaches that use various features like metadata, color, shape, texture features. But the Deep Convolutional Neural Network (DCNN) and transfer learning-based pre-trained CNN models are not explored much for Image spam classification. Therefore, in this work, 2 DCNN models along with few pre-trained ImageNet architectures like VGG19, Xception are trained on 3 different datasets. The effect of employing a Cost-sensitive learning approach to handle data imbalance is also studied. Some of the proposed models in this work achieves an accuracy up to 99% with zero false positive rate in best case.

/pdf/deep-convolutional-neural-networks-for-image-spam-3ubed6uf7g.pdf

A. Shashank

Papers

Identifying epiphytes in drones photos with a conditional generative adversarial network (c-gan)

Effect of Annotation and Loss Function on Epiphyte Identification using Conditional Generative Adversarial Network

Deep Convolutional Neural Networks for Image Spam Classification