Data protection from malicious attacks and misuse has become a crucial issue. Various types of data, including images, videos, audio and text documents, have given cause for the development of different methods for their protection. Cryptography, digital signatures and steganography are the most well known technologies used to protect data. During the last decade, digital watermarking technology has also been utilized as an alternative to prevent media forgery and tampering or falsification to ensure both copyright and authentication. Much work has been done to protect images, videos and audio but only a few algorithms have been considered for text document protection with digital watermarking. However, our survey observed that available text watermarking algorithms are neither robust nor imperceptible and as such remain unsecured methods of protection. Hence, research to improve the performance of text watermarking algorithms is required. This paper reviews current watermarking algorithms for text documents and categorizes text watermarking methods based on the way the text was treated during the watermarking process. It also discusses merits and demerits of available methods as well as recent proposed methods for evaluating text watermarking systems and the need for further research on digital text watermarking.

Numeral recognition is considered an essential preliminary step for optical character recognition, document understanding, and others. Although several handwritten numeral recognition algorithms have been proposed so far, achieving adequate recognition accuracy and execution time remain challenging to date. In particular, recognition accuracy depends on the features extraction mechanism. As such, a fast and robust numeral recognition method is essential, which meets the desired accuracy by extracting the features efficiently while maintaining fast implementation time. Furthermore, to date most of the existing studies are focused on evaluating their methods based on clean environments, thus limiting understanding of their potential application in more realistic noise environments. Therefore, finding a feasible and accurate handwritten numeral recognition method that is accurate in the more practical noisy environment is crucial. To this end, this paper proposes a new scheme for handwritten numeral recognition using Hybrid orthogonal polynomials. Gradient and smoothed features are extracted using the hybrid orthogonal polynomial. To reduce the complexity of feature extraction, the embedded image kernel technique has been adopted. In addition, support vector machine is used to classify the extracted features for the different numerals. The proposed scheme is evaluated under three different numeral recognition datasets: Roman, Arabic, and Devanagari. We compare the accuracy of the proposed numeral recognition method with the accuracy achieved by the state-of-the-art recognition methods. In addition, we compare the proposed method with the most updated method of a convolutional neural network. The results show that the proposed method achieves almost the highest recognition accuracy in comparison with the existing recognition methods in all the scenarios considered. Importantly, the results demonstrate that the proposed method is robust against the noise distortion and outperforms the convolutional neural network considerably, which signifies the feasibility and the effectiveness of the proposed approach in comparison to the state-of-the-art recognition methods under both clean noise and more realistic noise environments.

Automatic plant growth monitoring has received considerable attention in recent years. The demand in this field has created various opportunities, especially for automatic classification using deep learning methods. In this paper, the efficiency of deep learning algorithms in classifying the growth stage of chili plants is studied. Chili is one of the high cash value crops, and automatic identification of chili plant growth stages is essential for crop productivity. Nevertheless, the study on automatic chili plant growth stage classification using deep learning approaches is not widely explored, and this is due to the unavailability of public datasets on the chili plant growth stages. Various deep learning methods, namely Inception V3, ResNet50, and VGG16, were used in the study, and the results have shown that these methods performed well in terms of accuracy and stability when tested on a dataset that consists of 2,320 images of Capsicum annum 'Bird's Eye' plants of various growth stages and imaging conditions. Nevertheless, the results have also shown that the deep learning methods have difficulty classifying images with a complex background where more than one chili plant was captured in an image.