Evaluation of Convolutional Neural Network For Image Classification with Agricultural and Urban Datasets

TL;DR

This paper develops a custom CNN with advanced architectural features and evaluates its performance on diverse agricultural and urban image datasets, demonstrating competitive accuracy and efficiency for real-world applications.

Contribution

The paper introduces a novel CNN architecture with residual connections and attention mechanisms tailored for multi-domain image classification tasks.

Findings

CustomCNN achieves competitive accuracy on multiple datasets.

Architectural design choices significantly impact model performance.

The model is computationally efficient for practical deployment.

Abstract

This paper presents the development and evaluation of a custom Convolutional Neural Network (CustomCNN) created to study how architectural design choices affect multi-domain image classification tasks. The network uses residual connections, Squeeze-and-Excitation attention mechanisms, progressive channel scaling, and Kaiming initialization to improve its ability to represent data and speed up training. The model is trained and tested on five publicly available datasets: unauthorized vehicle detection, footpath encroachment detection, polygon-annotated road damage and manhole detection, MangoImageBD and PaddyVarietyBD. A comparison with popular CNN architectures shows that the CustomCNN delivers competitive performance while remaining efficient in computation. The results underscore the importance of thoughtful architectural design for real-world Smart City and agricultural imaging applications.