Optimizing VGG16 deep learning model with enhanced hunger games search for logo classification

Abstract

Accurate classification of logos is a challenging task in image recognition due to variations in logo size, orientation, and background complexity. Deep learning models, such as VGG16, have demonstrated promising results in handling such tasks. However, their performance is highly dependent on optimal hyperparameter settings, whose fine-tuning is both labor-intensive and time-consuming. Swarm intelligence algorithms have been widely adopted to solve many highly nonlinear, multimodal problems and have succeeded significantly. The Hunger Games Search (HGS) is a recent swarm intelligence algorithm that has shown good performance across various applications. However, the standard HGS still faces limitations, such as restricted population diversity and a tendency to get trapped in local optima, which can hinder its effectiveness. In this paper, we propose an optimized deep learning architecture called EHGS-VGG16 designed based on the VGG16 model and boosted by an enhanced Hunger Games Search (EHGS) algorithm for hyperparameter tuning. The proposed enhancement to HGS involves modified search strategies, incorporating the concepts of "local best" and a "local escaping mechanism" to improve its exploration capability. To validate our approach, the evaluation is conducted in three folds. First, the EHGS algorithm is evaluated through 30 real-valued benchmark functions from the IEEE CEC2014 suite. Second, a custom-developed VGG16 model is tested on the Flickr-27 logo classification dataset and compared against state-of-the-art deep learning models such as ResNet50V2, InceptionV3, DenseNet121, EfficientNetB0, and MobileNetV2. Finally, EHGS is integrated into the VGG16 model to optimize its hyperparameters. The experimental results show that VGG16 outperformed the other counterparts with an accuracy of 0.956966, a precision of 0.957137, and a recall of 0.956966. Moreover, the integration of EHGS further improved classification quality by 3%. These findings highlight the potential of combining evolutionary optimization techniques with deep learning for enhanced accuracy in log classification tasks.

Keywords: Computer vision; Convolution neural network; Hunger games search; Hyperparameters; Logo classification; Metaheuristics.

Fig. 1

Dynamic range of in HGS over 100 iterations, demonstrating controlled exploration and focused exploitation.

Algorithm 1

Pseudo-code of HGS

Fig. 2

Flowchart of the original hunger games search algorithm.

Fig. 3

Architecture of the VGG16 model, comprising 13 convolutional layers and 3 fully connected layers.

Fig. 4

The process of generating object proposals using selective search.

Fig. 5

Examples of IoU scores in object detection, illustrating various cases: no overlap, poor overlap, good overlap, and excellent overlap.

Algorithm 2

Pseudo-code of the enhanced HGS (EHGS)

Fig. 6

Convergence and diversity curves of HGS variants on sample of CEC2014 benchmarks.

Fig. 7

Box-and-whiskers plot of deep learning model performance in terms of classification quality and inference time.

Fig. 8

Bar chart of classification metrics reflecting results in Table 9.

Fig. 9

Learning and validation performance trends for VGG16, DensNet121, EfficientNetV0, and InceptionV3.

Fig. 10

Learning and validation performance trends for MobileNetV2, ResNet, and VGG16-NP.

Fig. 11

Bar chart comparing the classification metrics for predefined parameters, Basic HGS, and EHGS as detailed in Table 12.

Fig. 12

Convergence curves for HGS and EHGS for hyperparameter tuning of the VGG16 model over 20 iterations, averaged across 5 runs.