Automatic machine-based Facial Expression Analysis (FEA) has made substantial progress in the past few decades driven by its importance for applications in psychology, security, health, entertainment, and human–computer interaction. The vast majority of completed FEA studies are based on nonoccluded faces collected in a controlled laboratory environment. Automatic expression recognition tolerant to partial occlusion remains less understood, particularly in real-world scenarios. In recent years, efforts investigating techniques to handle partial occlusion for FEA have seen an increase. The context is right for a comprehensive perspective of these developments and the state of the art from this perspective. This survey provides such a comprehensive review of recent advances in dataset creation, algorithm development, and investigations of the effects of occlusion critical for robust performance in FEA systems. It outlines existing challenges in overcoming partial occlusion and discusses possible opportunities in advancing the technology. To the best of our knowledge, it is the first FEA survey dedicated to occlusion and aimed at promoting better-informed and benchmarked future work.

In-field mango fruit sizing is useful for estimation of fruit maturation and size distribution, informing the decision to harvest, harvest resourcing (e.g., tray insert sizes), and marketing. In-field machine vision imaging has been used for fruit count, but assessment of fruit size from images also requires estimation of camera-to-fruit distance. Low cost examples of three technologies for assessment of camera to fruit distance were assessed: a RGB-D (depth) camera, a stereo vision camera and a Time of Flight (ToF) laser rangefinder. The RGB-D camera was recommended on cost and performance, although it functioned poorly in direct sunlight. The RGB-D camera was calibrated, and depth information matched to the RGB image. To detect fruit, a cascade detection with histogram of oriented gradients (HOG) feature was used, then Otsu’s method, followed by color thresholding was applied in the CIE L*a*b* color space to remove background objects (leaves, branches etc.). A one-dimensional (1D) filter was developed to remove the fruit pedicles, and an ellipse fitting method employed to identify well-separated fruit. Finally, fruit lineal dimensions were calculated using the RGB-D depth information, fruit image size and the thin lens formula. A Root Mean Square Error (RMSE) = 4.9 and 4.3 mm was achieved for estimated fruit length and width, respectively, relative to manual measurement, for which repeated human measures were characterized by a standard deviation of 1.2 mm. In conclusion, the RGB-D method for rapid in-field mango fruit size estimation is practical in terms of cost and ease of use, but cannot be used in direct intense sunshine. We believe this work represents the first practical implementation of machine vision fruit sizing in field, with practicality gauged in terms of cost and simplicity of operation.

An intelligent computer-aided diagnosis system can be very helpful for radiologist in detecting and diagnosing microcalcification patterns earlier and faster than typical screening programs. In this paper, we present a system based on fuzzy-neural and feature extraction techniques for detecting and diagnosing microcalcifications' patterns in digital mammograms. We have investigated and analyzed a number of feature extraction techniques and found that a combination of three features (such as entropy, standard deviation and number of pixels) is the best combination to distinguish a benign microcalcification pattern from one that is malignant. A fuzzy technique in conjunction with three features was used to detect a microcalcification pattern and a neural network was used to classify it into benign/malignant. The system was developed on a Microsoft Windows platform. It is an easy-to-use intelligent system that gives the user options to diagnose, detect, enlarge, zoom and measure distances of areas in digital mammograms.

Rainfall prediction targets the determination of rainfall conditions over a specific location. It is considered vital for the agricultural industry and other industries. In this study, we propose a new forecasting method that uses a deep Convolutional Neural Network (CNN) to predict monthly rainfall for a selected location in eastern Australia. To our knowledge, this is the first time applying a deep CNN in predicting monthly rainfall. The proposed approach was compared against the Australian Community Climate and Earth-System Simulator-Seasonal Prediction System (ACCESS), which is a forecasting model released by the Bureau of Meteorology (BOM). In addition, the CNN was compared against a conventional Multi-Layered Perceptron (MLP). Better Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Pearson correlation (r) and Nash Suttcliff coefficient of efficiency (NSE) values were obtained with the proposed CNN. A difference of 37.006 mm was obtained in terms of RMSE compared to ACCESS and 15.941 compared to conventional MLP. Further investigation revealed that the CNN was generally performing better in months with higher annual averages, while ACCESS was performing better in months with low annual averages. The generated output is promising and can be widely extended in this type of applications.

This paper presents the impact of automatic feature extraction used in a deep learning architecture such as Convolutional Neural Network (CNN). Recently CNN has become a very popular tool for image classification which can automatically extract features, learn and classify them. It is a common belief that CNN can always perform better than other well-known classifiers. However, there is no systematic study which shows that automatic feature extraction in CNN is any better than other simple feature extraction techniques, and there is no study which shows that other simple neural network architectures cannot achieve same accuracy as CNN. In this paper, a systematic study to investigate CNN's feature extraction is presented. CNN with automatic feature extraction is firstly evaluated on a number of benchmark datasets and then a simple traditional Multi-Layer Perceptron (MLP) with full image, and manual feature extraction are evaluated on the same benchmark datasets. The purpose is to see whether feature extraction in CNN performs any better than a simple feature with MLP and full image with MLP. Many experiments were systematically conducted by varying number of epochs and hidden neurons. The experimental results revealed that traditional MLP with suitable parameters can perform as good as CNN or better in certain cases.