---
pipeline_tag: image-classification
license: apache-2.0
---

# Model Card: Fine-Tuned InceptionV3 for Human Bodypart Image Classification

This CNN model was developed to perform human bodypart classification for forensic purposes.

## Model Details

### Model Description

- **Funded by:** National Institute of Justice
- **Model type:** CNNs for Image Classification
- **Base Model:** InceptionV3 pretrained on ImageNet

## Dataset

- Dataset Name: Human Decomposition Image Dataset
- Source: The dataset used in this study was obtained from the Forensic Anthropology Center (FAC) at the University of Tennessee, Knoxville, but due to privacy considerations, it is not available for public access. Please reach out to obtain access.
- Classes: arm, hand, foot, legs, fullbody, head, backside, torso, stake, and plastic. stake and plastic classes were
included for filtering out images where bodyparts are covered with plastic or images showing stake with unanonymized donor IDs,
which is often the case in forensic anthropology.

## Usage
```python
from tensorflow.keras.models import load_model
import numpy as np
from tensorflow.keras.preprocessing.image import img_to_array, load_img

# Load the entire model
model = load_model('inception_acc_0.989001-_val_acc_0.98252.h5')  

# Load and preprocess an image
img = load_img('path_to_image.jpg', target_size=(299, 299))  # adjust size as per model input
img = img_to_array(img)  # convert to numpy array
img = np.expand_dims(img, axis=0)  # add batch dimension
img = img / 255.0  # normalize pixel values if needed

# Make predictions
predictions = model.predict(img)

# Use argmax to get the class label 
predicted_class = np.argmax(predictions, axis=1)
```