Nature is filled with various living organisms, ranging from micron scale fungi to large scale vertebrates, which possess unique adhesion characteristics, including self-cleaning, antifouling, and reusability in both wet and dry environments. Inspired from the natural adhesives, humans have endeavored to mimic and acquire those adhesion characteristics in artificially designed adhesives. Over several decades, researchers have employed various fabrication techniques and have used a variety of materials, predominantly polymers, to manufacture artificial adhesives which emulate the fundamental design aspects of the bioadhesion to match their adhesion performance. In this review, we briefly discuss the fundamentals aspects of adhesion, biomimetic design principles (derived from geckos, mussels, octopuses, and tree frogs), state of the art adhesion performance of the fabricated adhesives, their applications, and future outlook for the polymer-based adhesives both under dry and wet conditions.
Recurrent units and complex gated layers are key components of most text recognition models. Their sequential nature and complex mechanisms require large labelled training datasets, high computational requirements and lead to slower inference times. In this paper, we present an Efficient And Scalable TExt Recognizer (EASTER) to perform optical character recognition on both machine printed and handwritten text. Our model utilises only 1-D convolutional layers without any recurrence or complex gating mechanisms. Our proposed architecture achieves performance similar to best performing recurrent architectures by using only 4% of training data for offline handwritten text recognition task. We present results of our model on different machine printed text recognition datasets as well. We also showcase improvements over the current best results on line level offline handwritten text recognition task. Our work presents a highly scalable and deployable model for real-world settings while being highly performant.
The main objective of the proposed paper is to develop an energy meter which is totally based upon the GSM system and used to reduce the human efforts consumed during the door to door billing. We can use this system instead of door to door billing system as the power consumed in this will also be displayed to the consumers so there will be minimum chances of errors. This system is based on microcontroller here we are using atmega16 microcontroller. This gives all the controlling over the equipments connected to the system. Thus we are trying to present an idea towards the minimization of technical errors and to reduce human dependency at the same time. With the help of this project we are aiming to receive the monthly energy consumption from a remote location directly to a centralized office. In this way we can reduce human efforts needed to record the meter readings which are till now recorded by visiting every home individually.
Convolutional Neural Networks (CNN) have shown promising results for the task of Handwritten Text Recognition (HTR) but they still fall behind Recurrent Neural Networks (RNNs)/Transformer based models in terms of performance. In this paper, we propose a CNN based architecture that bridges this gap. Our work, Easter2.0, is composed of multiple layers of 1D Convolution, Batch Normalization, ReLU, Dropout, Dense Residual connection, Squeeze-and-Excitation module and make use of Connectionist Temporal Classification (CTC) loss. In addition to the Easter2.0 architecture, we propose a simple and effective data augmentation technique 'Tiling and Corruption (T ACo)' relevant for the task of HTR/OCR. Our work achieves state-of-the-art results on IAM handwriting database when trained using only publicly available training data. In our experiments, we also present the impact of T ACo augmentations and Squeeze-and-Excitation (SE) on text recognition accuracy. We further show that Easter2.0 is suitable for few-shot learning tasks and outperforms current best methods including Transformers when trained on limited amount of annotated data. Code and model is available at: https://github.com/kartikgill/Easter2.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.