cite image source

paper/paper.md

@@ -45,7 +45,7 @@ The app also provides information on how to dispose of the waste and what recycl
 
 The classification models are then converted into a lite format, such as [TFLite](https://www.tensorflow.org/lite/guide), which enables them to be used on mobile devices with limited resources. This format allows for fast loading times, smaller size, and compatibility with various programming languages and platforms. \autoref{fig:deep_waste_app_workflow} describes the overall workflow of the app.
 
-![App Workflow\label{fig:deep_waste_app_workflow}](app-workflow.png){width="100%"}[@kunwar_suman_2023]
+![App Workflow [@kunwar_suman_2023]\label{fig:deep_waste_app_workflow}](app-workflow.png){width="100%"}
 
 
 The app's user interface is designed to be user-friendly and intuitive, making it easy for anyone to use. It can also be used in conjunction with other waste management services such as waste collection and recycling services. In the progress tracker screen, users can monitor their progress towards rewards and receive tips on managing household waste, as shown in \autoref{fig:progress_tracker_screen}.