A Proposed Framework for Recognition of Handwritten Cursive English Characters using DAG-CNN

<p class="p1">Shopping of day-to-day items and keeping track of the shopping list can be a tedious and a time-consuming procedure, especially if it has to be done frequently. mySmartCart is a mobile application design proposed to transform the traditional way of writing a shopping list to a digitalized smart list which implements voice recognition and handwriting recognition for processing the natural language input of the user. The system design comprises four modules: i) input- which takes voice and handwritten list image input from the user; ii) processing- natural language processing of input data and converted to digital shopping list; iii) classification - list items classified into respective categories using machine learning algorithms; iv) output - searching on e-commerce applications and adding to shopping cart. The design proposed utilizes natural languages to communicate with the user thus enhancing their shopping experience. Google cloud speech recognition and tesseract optical character recognition (OCR) for natural language processing have been utilized in the prototype along with Support Vector Machine classifier for categorization.</p>

show abstract

“…Directed Acyclic Graph Convolutional Neural Network (DAG-CNN) [34] Handling of the hand-crafted features problem is done. 93% accuracy achieved.…”

Section: Classification Algorithmmentioning

confidence: 99%

mySmartCart: a smart shopping list for day-to-day supplies

Nanjappa¹,

Prakash²,

Burle³

et al. 2023

IJ-AI

View full text Add to dashboard Cite

show abstract

“…The paper has given a brief study of the K -means clustering algorithm for topic identification and provided a comparative study of the results of cluster analysis for small and large documents. Bhagyashree P V et al in 2019 [19] used an advanced deep learning technique DAG-CNN(Directed Acyclic Graph Convolutional neural network) for handwritten character recognition. The given method overcomes some of the disadvantages of CNN, like misclassifying identical cursive words.…”

Section: IImentioning

confidence: 99%

Digitizing Notes using Optical Character Recognition and Automatic Topic Identification and Classification using Natural Language Processing

Kulkarni,

Madurwar,

Narlawar

et al. 2023

IJRASET

View full text Add to dashboard Cite

In today’s world digital documents are a major part of everyone’s life as they have a wide scope of usage. However handwritten notes still contain loads of important and valuable information. In our research, we explore the different methods of Optical Character Recognition, or OCR which can be used for digitizing manual notes. Along with it we deep dive into the concept of Topic Detection and Identification and methods to implement it which are useful for extracting the crux of any document or piece of information. With the aim of integrating both processes into a single system, we study various algorithms involving neural networks like ANN, RNN, and CNN, and methods such as Tesseract, KNN, and LSTM that are used for implementing OCR while techniques such as K means clustering, TF-IDF, LDA and LINGO have been employed to perform topic detection and identification. Based on our study and results from various papers, we have decided to use CNN for OCR

show abstract

“…Such a world may have rich data from which information can be extracted. Different fields such as Machine Learning (ML), Database Management System (DBMS) [9], Data Mining (DM), Pattern Recognition (PR) [10], and Big Data Analytics (BD) [11] require advanced techniques of dealing with data, which vary widely in their range. Recent years have seen China enter the aging community.…”

Section: Introductionmentioning

confidence: 99%

Secure Smart Wearable Computing through Artificial Intelligence-Enabled Internet of Things and Cyber-Physical Systems for Health Monitoring

Ramasamy

Khan

Shah

et al. 2022

Sensors

View full text Add to dashboard Cite

The functionality of the Internet is continually changing from the Internet of Computers (IoC) to the “Internet of Things (IoT)”. Most connected systems, called Cyber-Physical Systems (CPS), are formed from the integration of numerous features such as humans and the physical environment, smart objects, and embedded devices and infrastructure. There are a few critical problems, such as security risks and ethical issues that could affect the IoT and CPS. When every piece of data and device is connected and obtainable on the network, hackers can obtain it and utilise it for different scams. In medical healthcare IoT-CPS, everyday medical and physical data of a patient may be gathered through wearable sensors. This paper proposes an AI-enabled IoT-CPS which doctors can utilise to discover diseases in patients based on AI. AI was created to find a few disorders such as Diabetes, Heart disease and Gait disturbances. Each disease has various symptoms among patients or elderly. Dataset is retrieved from the Kaggle repository to execute AI-enabled IoT-CPS technology. For the classification, AI-enabled IoT-CPS Algorithm is used to discover diseases. The experimental results demonstrate that compared with existing algorithms, the proposed AI-enabled IoT-CPS algorithm detects patient diseases and fall events in elderly more efficiently in terms of Accuracy, Precision, Recall and F-measure.

show abstract

A Proposed Framework for Recognition of Handwritten Cursive English Characters using DAG-CNN

Cited by 15 publications

References 12 publications

mySmartCart: a smart shopping list for day-to-day supplies

mySmartCart: a smart shopping list for day-to-day supplies

Digitizing Notes using Optical Character Recognition and Automatic Topic Identification and Classification using Natural Language Processing

Secure Smart Wearable Computing through Artificial Intelligence-Enabled Internet of Things and Cyber-Physical Systems for Health Monitoring

Contact Info

Product

Resources

About